diff --git a/Makefile b/Makefile
index 3b9e4658d31f..a056dba5ede0 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 20
-SUBLEVEL = 3
+SUBLEVEL = 4
 EXTRAVERSION =
 NAME = Shy Crocodile
 
@@ -967,6 +967,7 @@ ifdef CONFIG_STACK_VALIDATION
   endif
 endif
 
+PHONY += prepare0
 
 ifeq ($(KBUILD_EXTMOD),)
 core-y		+= kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/
@@ -1075,8 +1076,7 @@ scripts: scripts_basic scripts_dtc asm-generic gcc-plugins $(autoksyms_h)
 # archprepare is used in arch Makefiles and when processed asm symlink,
 # version.h and scripts_basic is processed / created.
 
-# Listed in dependency order
-PHONY += prepare archprepare prepare0 prepare1 prepare2 prepare3
+PHONY += prepare archprepare prepare1 prepare2 prepare3
 
 # prepare3 is used to check if we are building in a separate output directory,
 # and if so do:
@@ -1545,9 +1545,6 @@ else # KBUILD_EXTMOD
 
 # We are always building modules
 KBUILD_MODULES := 1
-PHONY += crmodverdir
-crmodverdir:
-	$(cmd_crmodverdir)
 
 PHONY += $(objtree)/Module.symvers
 $(objtree)/Module.symvers:
@@ -1559,7 +1556,7 @@ $(objtree)/Module.symvers:
 
 module-dirs := $(addprefix _module_,$(KBUILD_EXTMOD))
 PHONY += $(module-dirs) modules
-$(module-dirs): crmodverdir $(objtree)/Module.symvers
+$(module-dirs): prepare $(objtree)/Module.symvers
 	$(Q)$(MAKE) $(build)=$(patsubst _module_%,%,$@)
 
 modules: $(module-dirs)
@@ -1600,7 +1597,8 @@ help:
 
 # Dummies...
 PHONY += prepare scripts
-prepare: ;
+prepare:
+	$(cmd_crmodverdir)
 scripts: ;
 endif # KBUILD_EXTMOD
 
@@ -1724,17 +1722,14 @@ endif
 
 # Modules
 /: prepare scripts FORCE
-	$(cmd_crmodverdir)
 	$(Q)$(MAKE) KBUILD_MODULES=$(if $(CONFIG_MODULES),1) \
 	$(build)=$(build-dir)
 # Make sure the latest headers are built for Documentation
 Documentation/ samples/: headers_install
 %/: prepare scripts FORCE
-	$(cmd_crmodverdir)
 	$(Q)$(MAKE) KBUILD_MODULES=$(if $(CONFIG_MODULES),1) \
 	$(build)=$(build-dir)
 %.ko: prepare scripts FORCE
-	$(cmd_crmodverdir)
 	$(Q)$(MAKE) KBUILD_MODULES=$(if $(CONFIG_MODULES),1)   \
 	$(build)=$(build-dir) $(@:.ko=.o)
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
index 7d94c1fa592a..7f799cb5668e 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
@@ -28,6 +28,23 @@
 		method = "smc";
 	};
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		/*
+		 * This area matches the mapping done with a
+		 * mainline U-Boot, and should be updated by the
+		 * bootloader.
+		 */
+
+		psci-area@4000000 {
+			reg = <0x0 0x4000000 0x0 0x200000>;
+			no-map;
+		};
+	};
+
 	ap806 {
 		#address-cells = <2>;
 		#size-cells = <2>;
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 2dafd936d84d..bc2327d4a505 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -24,6 +24,8 @@
 
 /* Hyp Configuration Register (HCR) bits */
 #define HCR_FWB		(UL(1) << 46)
+#define HCR_API		(UL(1) << 41)
+#define HCR_APK		(UL(1) << 40)
 #define HCR_TEA		(UL(1) << 37)
 #define HCR_TERR	(UL(1) << 36)
 #define HCR_TLOR	(UL(1) << 35)
@@ -87,6 +89,7 @@
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
 			 HCR_FMO | HCR_IMO)
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
+#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 4471f570a295..b207a2ce4bc6 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -496,10 +496,9 @@ ENTRY(el2_setup)
 #endif
 
 	/* Hyp configuration. */
-	mov	x0, #HCR_RW			// 64-bit EL1
+	mov_q	x0, HCR_HOST_NVHE_FLAGS
 	cbz	x2, set_hcr
-	orr	x0, x0, #HCR_TGE		// Enable Host Extensions
-	orr	x0, x0, #HCR_E2H
+	mov_q	x0, HCR_HOST_VHE_FLAGS
 set_hcr:
 	msr	hcr_el2, x0
 	isb
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index f0e6ab8abe9c..ba6b41790fcd 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -14,6 +14,7 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
+#include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/memory.h>
@@ -43,7 +44,7 @@ static __init u64 get_kaslr_seed(void *fdt)
 	return ret;
 }
 
-static __init const u8 *get_cmdline(void *fdt)
+static __init const u8 *kaslr_get_cmdline(void *fdt)
 {
 	static __initconst const u8 default_cmdline[] = CONFIG_CMDLINE;
 
@@ -109,7 +110,7 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 * Check if 'nokaslr' appears on the command line, and
 	 * return 0 if that is the case.
 	 */
-	cmdline = get_cmdline(fdt);
+	cmdline = kaslr_get_cmdline(fdt);
 	str = strstr(cmdline, "nokaslr");
 	if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
 		return 0;
@@ -169,5 +170,8 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21;
 	module_alloc_base &= PAGE_MASK;
 
+	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
+	__flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed));
+
 	return offset;
 }
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 7cc175c88a37..f6e02cc4d856 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -157,7 +157,7 @@ static void __hyp_text __deactivate_traps_nvhe(void)
 	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
 
 	write_sysreg(mdcr_el2, mdcr_el2);
-	write_sysreg(HCR_RW, hcr_el2);
+	write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
 	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
 }
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 8272ea4c7264..6207b41473a0 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -3184,6 +3184,7 @@ config MIPS32_O32
 config MIPS32_N32
 	bool "Kernel support for n32 binaries"
 	depends on 64BIT
+	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select COMPAT
 	select MIPS32_COMPAT
 	select SYSVIPC_COMPAT if SYSVIPC
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index 6054d49e608e..fe3773539eff 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -173,6 +173,31 @@ void __init plat_mem_setup(void)
 	pm_power_off = bcm47xx_machine_halt;
 }
 
+#ifdef CONFIG_BCM47XX_BCMA
+static struct device * __init bcm47xx_setup_device(void)
+{
+	struct device *dev;
+	int err;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+
+	err = dev_set_name(dev, "bcm47xx_soc");
+	if (err) {
+		pr_err("Failed to set SoC device name: %d\n", err);
+		kfree(dev);
+		return NULL;
+	}
+
+	err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (err)
+		pr_err("Failed to set SoC DMA mask: %d\n", err);
+
+	return dev;
+}
+#endif
+
 /*
  * This finishes bus initialization doing things that were not possible without
  * kmalloc. Make sure to call it late enough (after mm_init).
@@ -183,6 +208,10 @@ void __init bcm47xx_bus_setup(void)
 	if (bcm47xx_bus_type == BCM47XX_BUS_TYPE_BCMA) {
 		int err;
 
+		bcm47xx_bus.bcma.dev = bcm47xx_setup_device();
+		if (!bcm47xx_bus.bcma.dev)
+			panic("Failed to setup SoC device\n");
+
 		err = bcma_host_soc_init(&bcm47xx_bus.bcma);
 		if (err)
 			panic("Failed to initialize BCMA bus (err %d)", err);
@@ -235,6 +264,8 @@ static int __init bcm47xx_register_bus_complete(void)
 #endif
 #ifdef CONFIG_BCM47XX_BCMA
 	case BCM47XX_BUS_TYPE_BCMA:
+		if (device_register(bcm47xx_bus.bcma.dev))
+			pr_err("Failed to register SoC device\n");
 		bcma_bus_register(&bcm47xx_bus.bcma.bus);
 		break;
 #endif
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index dfb95cffef3e..a3cf68538f3d 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -96,7 +96,7 @@ static void octeon_kexec_smp_down(void *ignored)
 	"	sync						\n"
 	"	synci	($0)					\n");
 
-	relocated_kexec_smp_wait(NULL);
+	kexec_reboot();
 }
 #endif
 
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
index f0bc3312ed11..c4ef1c31e0c4 100644
--- a/arch/mips/lantiq/irq.c
+++ b/arch/mips/lantiq/irq.c
@@ -224,9 +224,11 @@ static struct irq_chip ltq_eiu_type = {
 	.irq_set_type = ltq_eiu_settype,
 };
 
-static void ltq_hw_irqdispatch(int module)
+static void ltq_hw_irq_handler(struct irq_desc *desc)
 {
+	int module = irq_desc_get_irq(desc) - 2;
 	u32 irq;
+	int hwirq;
 
 	irq = ltq_icu_r32(module, LTQ_ICU_IM0_IOSR);
 	if (irq == 0)
@@ -237,7 +239,8 @@ static void ltq_hw_irqdispatch(int module)
 	 * other bits might be bogus
 	 */
 	irq = __fls(irq);
-	do_IRQ((int)irq + MIPS_CPU_IRQ_CASCADE + (INT_NUM_IM_OFFSET * module));
+	hwirq = irq + MIPS_CPU_IRQ_CASCADE + (INT_NUM_IM_OFFSET * module);
+	generic_handle_irq(irq_linear_revmap(ltq_domain, hwirq));
 
 	/* if this is a EBU irq, we need to ack it or get a deadlock */
 	if ((irq == LTQ_ICU_EBU_IRQ) && (module == 0) && LTQ_EBU_PCC_ISTAT)
@@ -245,49 +248,6 @@ static void ltq_hw_irqdispatch(int module)
 			LTQ_EBU_PCC_ISTAT);
 }
 
-#define DEFINE_HWx_IRQDISPATCH(x)					\
-	static void ltq_hw ## x ## _irqdispatch(void)			\
-	{								\
-		ltq_hw_irqdispatch(x);					\
-	}
-DEFINE_HWx_IRQDISPATCH(0)
-DEFINE_HWx_IRQDISPATCH(1)
-DEFINE_HWx_IRQDISPATCH(2)
-DEFINE_HWx_IRQDISPATCH(3)
-DEFINE_HWx_IRQDISPATCH(4)
-
-#if MIPS_CPU_TIMER_IRQ == 7
-static void ltq_hw5_irqdispatch(void)
-{
-	do_IRQ(MIPS_CPU_TIMER_IRQ);
-}
-#else
-DEFINE_HWx_IRQDISPATCH(5)
-#endif
-
-static void ltq_hw_irq_handler(struct irq_desc *desc)
-{
-	ltq_hw_irqdispatch(irq_desc_get_irq(desc) - 2);
-}
-
-asmlinkage void plat_irq_dispatch(void)
-{
-	unsigned int pending = read_c0_status() & read_c0_cause() & ST0_IM;
-	int irq;
-
-	if (!pending) {
-		spurious_interrupt();
-		return;
-	}
-
-	pending >>= CAUSEB_IP;
-	while (pending) {
-		irq = fls(pending) - 1;
-		do_IRQ(MIPS_CPU_IRQ_BASE + irq);
-		pending &= ~BIT(irq);
-	}
-}
-
 static int icu_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
 {
 	struct irq_chip *chip = &ltq_irq_type;
@@ -343,28 +303,10 @@ int __init icu_of_init(struct device_node *node, struct device_node *parent)
 	for (i = 0; i < MAX_IM; i++)
 		irq_set_chained_handler(i + 2, ltq_hw_irq_handler);
 
-	if (cpu_has_vint) {
-		pr_info("Setting up vectored interrupts\n");
-		set_vi_handler(2, ltq_hw0_irqdispatch);
-		set_vi_handler(3, ltq_hw1_irqdispatch);
-		set_vi_handler(4, ltq_hw2_irqdispatch);
-		set_vi_handler(5, ltq_hw3_irqdispatch);
-		set_vi_handler(6, ltq_hw4_irqdispatch);
-		set_vi_handler(7, ltq_hw5_irqdispatch);
-	}
-
 	ltq_domain = irq_domain_add_linear(node,
 		(MAX_IM * INT_NUM_IM_OFFSET) + MIPS_CPU_IRQ_CASCADE,
 		&irq_domain_ops, 0);
 
-#ifndef CONFIG_MIPS_MT_SMP
-	set_c0_status(IE_IRQ0 | IE_IRQ1 | IE_IRQ2 |
-		IE_IRQ3 | IE_IRQ4 | IE_IRQ5);
-#else
-	set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ0 | IE_IRQ1 |
-		IE_IRQ2 | IE_IRQ3 | IE_IRQ4 | IE_IRQ5);
-#endif
-
 	/* tell oprofile which irq to use */
 	ltq_perfcount_irq = irq_create_mapping(ltq_domain, LTQ_PERF_IRQ);
 
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index 2a5bb849b10e..288b58b00dc8 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -369,7 +369,9 @@ int __init octeon_msi_initialize(void)
 	int irq;
 	struct irq_chip *msi;
 
-	if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
+	if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_INVALID) {
+		return 0;
+	} else if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
 		msi_rcv_reg[0] = CVMX_PEXP_NPEI_MSI_RCV0;
 		msi_rcv_reg[1] = CVMX_PEXP_NPEI_MSI_RCV1;
 		msi_rcv_reg[2] = CVMX_PEXP_NPEI_MSI_RCV2;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 6f70d1b4bf36..14b0f5b6a373 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -755,11 +755,12 @@ SYSCALL_DEFINE0(rt_sigreturn)
 		if (restore_tm_sigcontexts(current, &uc->uc_mcontext,
 					   &uc_transact->uc_mcontext))
 			goto badframe;
-	}
+	} else
 #endif
-	/* Fall through, for non-TM restore */
-	if (!MSR_TM_ACTIVE(msr)) {
+	{
 		/*
+		 * Fall through, for non-TM restore
+		 *
 		 * Unset MSR[TS] on the thread regs since MSR from user
 		 * context does not have MSR active, and recheckpoint was
 		 * not called since restore_tm_sigcontexts() was not called
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 72bf446c3fee..6e29794573b7 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -361,8 +361,6 @@ void xen_timer_resume(void)
 {
 	int cpu;
 
-	pvclock_resume();
-
 	if (xen_clockevent != &xen_vcpuop_clockevent)
 		return;
 
@@ -379,12 +377,15 @@ static const struct pv_time_ops xen_time_ops __initconst = {
 };
 
 static struct pvclock_vsyscall_time_info *xen_clock __read_mostly;
+static u64 xen_clock_value_saved;
 
 void xen_save_time_memory_area(void)
 {
 	struct vcpu_register_time_memory_area t;
 	int ret;
 
+	xen_clock_value_saved = xen_clocksource_read() - xen_sched_clock_offset;
+
 	if (!xen_clock)
 		return;
 
@@ -404,7 +405,7 @@ void xen_restore_time_memory_area(void)
 	int ret;
 
 	if (!xen_clock)
-		return;
+		goto out;
 
 	t.addr.v = &xen_clock->pvti;
 
@@ -421,6 +422,11 @@ void xen_restore_time_memory_area(void)
 	if (ret != 0)
 		pr_notice("Cannot restore secondary vcpu_time_info (err %d)",
 			  ret);
+
+out:
+	/* Need pvclock_resume() before using xen_clocksource_read(). */
+	pvclock_resume();
+	xen_sched_clock_offset = xen_clocksource_read() - xen_clock_value_saved;
 }
 
 static void xen_setup_vsyscall_time_info(void)
diff --git a/block/partition-generic.c b/block/partition-generic.c
index d3d14e81fb12..5f8db5c5140f 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -249,9 +249,10 @@ struct device_type part_type = {
 	.uevent		= part_uevent,
 };
 
-static void delete_partition_rcu_cb(struct rcu_head *head)
+static void delete_partition_work_fn(struct work_struct *work)
 {
-	struct hd_struct *part = container_of(head, struct hd_struct, rcu_head);
+	struct hd_struct *part = container_of(to_rcu_work(work), struct hd_struct,
+					rcu_work);
 
 	part->start_sect = 0;
 	part->nr_sects = 0;
@@ -262,7 +263,8 @@ static void delete_partition_rcu_cb(struct rcu_head *head)
 void __delete_partition(struct percpu_ref *ref)
 {
 	struct hd_struct *part = container_of(ref, struct hd_struct, ref);
-	call_rcu(&part->rcu_head, delete_partition_rcu_cb);
+	INIT_RCU_WORK(&part->rcu_work, delete_partition_work_fn);
+	queue_rcu_work(system_wq, &part->rcu_work);
 }
 
 /*
diff --git a/crypto/authenc.c b/crypto/authenc.c
index 37f54d1b2f66..4be293a4b5f0 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -58,14 +58,22 @@ int crypto_authenc_extractkeys(struct crypto_authenc_keys *keys, const u8 *key,
 		return -EINVAL;
 	if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM)
 		return -EINVAL;
-	if (RTA_PAYLOAD(rta) < sizeof(*param))
+
+	/*
+	 * RTA_OK() didn't align the rtattr's payload when validating that it
+	 * fits in the buffer.  Yet, the keys should start on the next 4-byte
+	 * aligned boundary.  To avoid confusion, require that the rtattr
+	 * payload be exactly the param struct, which has a 4-byte aligned size.
+	 */
+	if (RTA_PAYLOAD(rta) != sizeof(*param))
 		return -EINVAL;
+	BUILD_BUG_ON(sizeof(*param) % RTA_ALIGNTO);
 
 	param = RTA_DATA(rta);
 	keys->enckeylen = be32_to_cpu(param->enckeylen);
 
-	key += RTA_ALIGN(rta->rta_len);
-	keylen -= RTA_ALIGN(rta->rta_len);
+	key += rta->rta_len;
+	keylen -= rta->rta_len;
 
 	if (keylen < keys->enckeylen)
 		return -EINVAL;
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 80a25cc04aec..4741fe89ba2c 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -279,7 +279,7 @@ static void authenc_esn_verify_ahash_done(struct crypto_async_request *areq,
 	struct aead_request *req = areq->data;
 
 	err = err ?: crypto_authenc_esn_decrypt_tail(req, 0);
-	aead_request_complete(req, err);
+	authenc_esn_request_complete(req, err);
 }
 
 static int crypto_authenc_esn_decrypt(struct aead_request *req)
diff --git a/crypto/sm3_generic.c b/crypto/sm3_generic.c
index 9a5c60f08aad..c0cf87ae7ef6 100644
--- a/crypto/sm3_generic.c
+++ b/crypto/sm3_generic.c
@@ -100,7 +100,7 @@ static void sm3_compress(u32 *w, u32 *wt, u32 *m)
 
 	for (i = 0; i <= 63; i++) {
 
-		ss1 = rol32((rol32(a, 12) + e + rol32(t(i), i)), 7);
+		ss1 = rol32((rol32(a, 12) + e + rol32(t(i), i & 31)), 7);
 
 		ss2 = ss1 ^ rol32(a, 12);
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index cb0cc8685076..84b055aa81ba 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -83,7 +83,7 @@
 #include <linux/uaccess.h>
 
 static DEFINE_IDR(loop_index_idr);
-static DEFINE_MUTEX(loop_index_mutex);
+static DEFINE_MUTEX(loop_ctl_mutex);
 
 static int max_part;
 static int part_shift;
@@ -630,18 +630,7 @@ static void loop_reread_partitions(struct loop_device *lo,
 {
 	int rc;
 
-	/*
-	 * bd_mutex has been held already in release path, so don't
-	 * acquire it if this function is called in such case.
-	 *
-	 * If the reread partition isn't from release path, lo_refcnt
-	 * must be at least one and it can only become zero when the
-	 * current holder is released.
-	 */
-	if (!atomic_read(&lo->lo_refcnt))
-		rc = __blkdev_reread_part(bdev);
-	else
-		rc = blkdev_reread_part(bdev);
+	rc = blkdev_reread_part(bdev);
 	if (rc)
 		pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n",
 			__func__, lo->lo_number, lo->lo_file_name, rc);
@@ -688,26 +677,30 @@ static int loop_validate_file(struct file *file, struct block_device *bdev)
 static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 			  unsigned int arg)
 {
-	struct file	*file, *old_file;
+	struct file	*file = NULL, *old_file;
 	int		error;
+	bool		partscan;
 
+	error = mutex_lock_killable(&loop_ctl_mutex);
+	if (error)
+		return error;
 	error = -ENXIO;
 	if (lo->lo_state != Lo_bound)
-		goto out;
+		goto out_err;
 
 	/* the loop device has to be read-only */
 	error = -EINVAL;
 	if (!(lo->lo_flags & LO_FLAGS_READ_ONLY))
-		goto out;
+		goto out_err;
 
 	error = -EBADF;
 	file = fget(arg);
 	if (!file)
-		goto out;
+		goto out_err;
 
 	error = loop_validate_file(file, bdev);
 	if (error)
-		goto out_putf;
+		goto out_err;
 
 	old_file = lo->lo_backing_file;
 
@@ -715,7 +708,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 
 	/* size of the new backing store needs to be the same */
 	if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
-		goto out_putf;
+		goto out_err;
 
 	/* and ... switch */
 	blk_mq_freeze_queue(lo->lo_queue);
@@ -726,15 +719,22 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 			     lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 	loop_update_dio(lo);
 	blk_mq_unfreeze_queue(lo->lo_queue);
-
+	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
+	mutex_unlock(&loop_ctl_mutex);
+	/*
+	 * We must drop file reference outside of loop_ctl_mutex as dropping
+	 * the file ref can take bd_mutex which creates circular locking
+	 * dependency.
+	 */
 	fput(old_file);
-	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
+	if (partscan)
 		loop_reread_partitions(lo, bdev);
 	return 0;
 
- out_putf:
-	fput(file);
- out:
+out_err:
+	mutex_unlock(&loop_ctl_mutex);
+	if (file)
+		fput(file);
 	return error;
 }
 
@@ -909,6 +909,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	int		lo_flags = 0;
 	int		error;
 	loff_t		size;
+	bool		partscan;
 
 	/* This is safe, since we have a reference from open(). */
 	__module_get(THIS_MODULE);
@@ -918,13 +919,17 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	if (!file)
 		goto out;
 
+	error = mutex_lock_killable(&loop_ctl_mutex);
+	if (error)
+		goto out_putf;
+
 	error = -EBUSY;
 	if (lo->lo_state != Lo_unbound)
-		goto out_putf;
+		goto out_unlock;
 
 	error = loop_validate_file(file, bdev);
 	if (error)
-		goto out_putf;
+		goto out_unlock;
 
 	mapping = file->f_mapping;
 	inode = mapping->host;
@@ -936,10 +941,10 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	error = -EFBIG;
 	size = get_loop_size(lo, file);
 	if ((loff_t)(sector_t)size != size)
-		goto out_putf;
+		goto out_unlock;
 	error = loop_prepare_queue(lo);
 	if (error)
-		goto out_putf;
+		goto out_unlock;
 
 	error = 0;
 
@@ -971,18 +976,22 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->lo_state = Lo_bound;
 	if (part_shift)
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
-	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
-		loop_reread_partitions(lo, bdev);
+	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
 
 	/* Grab the block_device to prevent its destruction after we
-	 * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev).
+	 * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev).
 	 */
 	bdgrab(bdev);
+	mutex_unlock(&loop_ctl_mutex);
+	if (partscan)
+		loop_reread_partitions(lo, bdev);
 	return 0;
 
- out_putf:
+out_unlock:
+	mutex_unlock(&loop_ctl_mutex);
+out_putf:
 	fput(file);
- out:
+out:
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
 	return error;
@@ -1025,39 +1034,31 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
 	return err;
 }
 
-static int loop_clr_fd(struct loop_device *lo)
+static int __loop_clr_fd(struct loop_device *lo, bool release)
 {
-	struct file *filp = lo->lo_backing_file;
+	struct file *filp = NULL;
 	gfp_t gfp = lo->old_gfp_mask;
 	struct block_device *bdev = lo->lo_device;
+	int err = 0;
+	bool partscan = false;
+	int lo_number;
 
-	if (lo->lo_state != Lo_bound)
-		return -ENXIO;
-
-	/*
-	 * If we've explicitly asked to tear down the loop device,
-	 * and it has an elevated reference count, set it for auto-teardown when
-	 * the last reference goes away. This stops $!~#$@ udev from
-	 * preventing teardown because it decided that it needs to run blkid on
-	 * the loopback device whenever they appear. xfstests is notorious for
-	 * failing tests because blkid via udev races with a losetup
-	 * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
-	 * command to fail with EBUSY.
-	 */
-	if (atomic_read(&lo->lo_refcnt) > 1) {
-		lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
-		mutex_unlock(&lo->lo_ctl_mutex);
-		return 0;
+	mutex_lock(&loop_ctl_mutex);
+	if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) {
+		err = -ENXIO;
+		goto out_unlock;
 	}
 
-	if (filp == NULL)
-		return -EINVAL;
+	filp = lo->lo_backing_file;
+	if (filp == NULL) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 
 	/* freeze request queue during the transition */
 	blk_mq_freeze_queue(lo->lo_queue);
 
 	spin_lock_irq(&lo->lo_lock);
-	lo->lo_state = Lo_rundown;
 	lo->lo_backing_file = NULL;
 	spin_unlock_irq(&lo->lo_lock);
 
@@ -1093,21 +1094,73 @@ static int loop_clr_fd(struct loop_device *lo)
 	module_put(THIS_MODULE);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
-	if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev)
-		loop_reread_partitions(lo, bdev);
+	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev;
+	lo_number = lo->lo_number;
 	lo->lo_flags = 0;
 	if (!part_shift)
 		lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
 	loop_unprepare_queue(lo);
-	mutex_unlock(&lo->lo_ctl_mutex);
+out_unlock:
+	mutex_unlock(&loop_ctl_mutex);
+	if (partscan) {
+		/*
+		 * bd_mutex has been held already in release path, so don't
+		 * acquire it if this function is called in such case.
+		 *
+		 * If the reread partition isn't from release path, lo_refcnt
+		 * must be at least one and it can only become zero when the
+		 * current holder is released.
+		 */
+		if (release)
+			err = __blkdev_reread_part(bdev);
+		else
+			err = blkdev_reread_part(bdev);
+		pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
+			__func__, lo_number, err);
+		/* Device is gone, no point in returning error */
+		err = 0;
+	}
 	/*
-	 * Need not hold lo_ctl_mutex to fput backing file.
-	 * Calling fput holding lo_ctl_mutex triggers a circular
+	 * Need not hold loop_ctl_mutex to fput backing file.
+	 * Calling fput holding loop_ctl_mutex triggers a circular
 	 * lock dependency possibility warning as fput can take
-	 * bd_mutex which is usually taken before lo_ctl_mutex.
+	 * bd_mutex which is usually taken before loop_ctl_mutex.
 	 */
-	fput(filp);
-	return 0;
+	if (filp)
+		fput(filp);
+	return err;
+}
+
+static int loop_clr_fd(struct loop_device *lo)
+{
+	int err;
+
+	err = mutex_lock_killable(&loop_ctl_mutex);
+	if (err)
+		return err;
+	if (lo->lo_state != Lo_bound) {
+		mutex_unlock(&loop_ctl_mutex);
+		return -ENXIO;
+	}
+	/*
+	 * If we've explicitly asked to tear down the loop device,
+	 * and it has an elevated reference count, set it for auto-teardown when
+	 * the last reference goes away. This stops $!~#$@ udev from
+	 * preventing teardown because it decided that it needs to run blkid on
+	 * the loopback device whenever they appear. xfstests is notorious for
+	 * failing tests because blkid via udev races with a losetup
+	 * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
+	 * command to fail with EBUSY.
+	 */
+	if (atomic_read(&lo->lo_refcnt) > 1) {
+		lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
+		mutex_unlock(&loop_ctl_mutex);
+		return 0;
+	}
+	lo->lo_state = Lo_rundown;
+	mutex_unlock(&loop_ctl_mutex);
+
+	return __loop_clr_fd(lo, false);
 }
 
 static int
@@ -1116,47 +1169,72 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	int err;
 	struct loop_func_table *xfer;
 	kuid_t uid = current_uid();
+	struct block_device *bdev;
+	bool partscan = false;
 
+	err = mutex_lock_killable(&loop_ctl_mutex);
+	if (err)
+		return err;
 	if (lo->lo_encrypt_key_size &&
 	    !uid_eq(lo->lo_key_owner, uid) &&
-	    !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-	if (lo->lo_state != Lo_bound)
-		return -ENXIO;
-	if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
-		return -EINVAL;
+	    !capable(CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto out_unlock;
+	}
+	if (lo->lo_state != Lo_bound) {
+		err = -ENXIO;
+		goto out_unlock;
+	}
+	if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
+	if (lo->lo_offset != info->lo_offset ||
+	    lo->lo_sizelimit != info->lo_sizelimit) {
+		sync_blockdev(lo->lo_device);
+		kill_bdev(lo->lo_device);
+	}
 
 	/* I/O need to be drained during transfer transition */
 	blk_mq_freeze_queue(lo->lo_queue);
 
 	err = loop_release_xfer(lo);
 	if (err)
-		goto exit;
+		goto out_unfreeze;
 
 	if (info->lo_encrypt_type) {
 		unsigned int type = info->lo_encrypt_type;
 
 		if (type >= MAX_LO_CRYPT) {
 			err = -EINVAL;
-			goto exit;
+			goto out_unfreeze;
 		}
 		xfer = xfer_funcs[type];
 		if (xfer == NULL) {
 			err = -EINVAL;
-			goto exit;
+			goto out_unfreeze;
 		}
 	} else
 		xfer = NULL;
 
 	err = loop_init_xfer(lo, xfer, info);
 	if (err)
-		goto exit;
+		goto out_unfreeze;
 
 	if (lo->lo_offset != info->lo_offset ||
 	    lo->lo_sizelimit != info->lo_sizelimit) {
+		/* kill_bdev should have truncated all the pages */
+		if (lo->lo_device->bd_inode->i_mapping->nrpages) {
+			err = -EAGAIN;
+			pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
+				__func__, lo->lo_number, lo->lo_file_name,
+				lo->lo_device->bd_inode->i_mapping->nrpages);
+			goto out_unfreeze;
+		}
 		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
 			err = -EFBIG;
-			goto exit;
+			goto out_unfreeze;
 		}
 	}
 
@@ -1188,15 +1266,20 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	/* update dio if lo_offset or transfer is changed */
 	__loop_update_dio(lo, lo->use_dio);
 
- exit:
+out_unfreeze:
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
 	if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) &&
 	     !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
-		loop_reread_partitions(lo, lo->lo_device);
+		bdev = lo->lo_device;
+		partscan = true;
 	}
+out_unlock:
+	mutex_unlock(&loop_ctl_mutex);
+	if (partscan)
+		loop_reread_partitions(lo, bdev);
 
 	return err;
 }
@@ -1204,12 +1287,15 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 static int
 loop_get_status(struct loop_device *lo, struct loop_info64 *info)
 {
-	struct file *file;
+	struct path path;
 	struct kstat stat;
 	int ret;
 
+	ret = mutex_lock_killable(&loop_ctl_mutex);
+	if (ret)
+		return ret;
 	if (lo->lo_state != Lo_bound) {
-		mutex_unlock(&lo->lo_ctl_mutex);
+		mutex_unlock(&loop_ctl_mutex);
 		return -ENXIO;
 	}
 
@@ -1228,17 +1314,17 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info)
 		       lo->lo_encrypt_key_size);
 	}
 
-	/* Drop lo_ctl_mutex while we call into the filesystem. */
-	file = get_file(lo->lo_backing_file);
-	mutex_unlock(&lo->lo_ctl_mutex);
-	ret = vfs_getattr(&file->f_path, &stat, STATX_INO,
-			  AT_STATX_SYNC_AS_STAT);
+	/* Drop loop_ctl_mutex while we call into the filesystem. */
+	path = lo->lo_backing_file->f_path;
+	path_get(&path);
+	mutex_unlock(&loop_ctl_mutex);
+	ret = vfs_getattr(&path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT);
 	if (!ret) {
 		info->lo_device = huge_encode_dev(stat.dev);
 		info->lo_inode = stat.ino;
 		info->lo_rdevice = huge_encode_dev(stat.rdev);
 	}
-	fput(file);
+	path_put(&path);
 	return ret;
 }
 
@@ -1322,10 +1408,8 @@ loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) {
 	struct loop_info64 info64;
 	int err;
 
-	if (!arg) {
-		mutex_unlock(&lo->lo_ctl_mutex);
+	if (!arg)
 		return -EINVAL;
-	}
 	err = loop_get_status(lo, &info64);
 	if (!err)
 		err = loop_info64_to_old(&info64, &info);
@@ -1340,10 +1424,8 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
 	struct loop_info64 info64;
 	int err;
 
-	if (!arg) {
-		mutex_unlock(&lo->lo_ctl_mutex);
+	if (!arg)
 		return -EINVAL;
-	}
 	err = loop_get_status(lo, &info64);
 	if (!err && copy_to_user(arg, &info64, sizeof(info64)))
 		err = -EFAULT;
@@ -1375,22 +1457,64 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg)
 
 static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 {
+	int err = 0;
+
 	if (lo->lo_state != Lo_bound)
 		return -ENXIO;
 
 	if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg))
 		return -EINVAL;
 
+	if (lo->lo_queue->limits.logical_block_size != arg) {
+		sync_blockdev(lo->lo_device);
+		kill_bdev(lo->lo_device);
+	}
+
 	blk_mq_freeze_queue(lo->lo_queue);
 
+	/* kill_bdev should have truncated all the pages */
+	if (lo->lo_queue->limits.logical_block_size != arg &&
+			lo->lo_device->bd_inode->i_mapping->nrpages) {
+		err = -EAGAIN;
+		pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
+			__func__, lo->lo_number, lo->lo_file_name,
+			lo->lo_device->bd_inode->i_mapping->nrpages);
+		goto out_unfreeze;
+	}
+
 	blk_queue_logical_block_size(lo->lo_queue, arg);
 	blk_queue_physical_block_size(lo->lo_queue, arg);
 	blk_queue_io_min(lo->lo_queue, arg);
 	loop_update_dio(lo);
-
+out_unfreeze:
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
-	return 0;
+	return err;
+}
+
+static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd,
+			   unsigned long arg)
+{
+	int err;
+
+	err = mutex_lock_killable(&loop_ctl_mutex);
+	if (err)
+		return err;
+	switch (cmd) {
+	case LOOP_SET_CAPACITY:
+		err = loop_set_capacity(lo);
+		break;
+	case LOOP_SET_DIRECT_IO:
+		err = loop_set_dio(lo, arg);
+		break;
+	case LOOP_SET_BLOCK_SIZE:
+		err = loop_set_block_size(lo, arg);
+		break;
+	default:
+		err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
+	}
+	mutex_unlock(&loop_ctl_mutex);
+	return err;
 }
 
 static int lo_ioctl(struct block_device *bdev, fmode_t mode,
@@ -1399,64 +1523,42 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	struct loop_device *lo = bdev->bd_disk->private_data;
 	int err;
 
-	err = mutex_lock_killable_nested(&lo->lo_ctl_mutex, 1);
-	if (err)
-		goto out_unlocked;
-
 	switch (cmd) {
 	case LOOP_SET_FD:
-		err = loop_set_fd(lo, mode, bdev, arg);
-		break;
+		return loop_set_fd(lo, mode, bdev, arg);
 	case LOOP_CHANGE_FD:
-		err = loop_change_fd(lo, bdev, arg);
-		break;
+		return loop_change_fd(lo, bdev, arg);
 	case LOOP_CLR_FD:
-		/* loop_clr_fd would have unlocked lo_ctl_mutex on success */
-		err = loop_clr_fd(lo);
-		if (!err)
-			goto out_unlocked;
-		break;
+		return loop_clr_fd(lo);
 	case LOOP_SET_STATUS:
 		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) {
 			err = loop_set_status_old(lo,
 					(struct loop_info __user *)arg);
+		}
 		break;
 	case LOOP_GET_STATUS:
-		err = loop_get_status_old(lo, (struct loop_info __user *) arg);
-		/* loop_get_status() unlocks lo_ctl_mutex */
-		goto out_unlocked;
+		return loop_get_status_old(lo, (struct loop_info __user *) arg);
 	case LOOP_SET_STATUS64:
 		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) {
 			err = loop_set_status64(lo,
 					(struct loop_info64 __user *) arg);
+		}
 		break;
 	case LOOP_GET_STATUS64:
-		err = loop_get_status64(lo, (struct loop_info64 __user *) arg);
-		/* loop_get_status() unlocks lo_ctl_mutex */
-		goto out_unlocked;
+		return loop_get_status64(lo, (struct loop_info64 __user *) arg);
 	case LOOP_SET_CAPACITY:
-		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
-			err = loop_set_capacity(lo);
-		break;
 	case LOOP_SET_DIRECT_IO:
-		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
-			err = loop_set_dio(lo, arg);
-		break;
 	case LOOP_SET_BLOCK_SIZE:
-		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
-			err = loop_set_block_size(lo, arg);
-		break;
+		if (!(mode & FMODE_WRITE) && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		/* Fall through */
 	default:
-		err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
+		err = lo_simple_ioctl(lo, cmd, arg);
+		break;
 	}
-	mutex_unlock(&lo->lo_ctl_mutex);
 
-out_unlocked:
 	return err;
 }
 
@@ -1570,10 +1672,8 @@ loop_get_status_compat(struct loop_device *lo,
 	struct loop_info64 info64;
 	int err;
 
-	if (!arg) {
-		mutex_unlock(&lo->lo_ctl_mutex);
+	if (!arg)
 		return -EINVAL;
-	}
 	err = loop_get_status(lo, &info64);
 	if (!err)
 		err = loop_info64_to_compat(&info64, arg);
@@ -1588,20 +1688,12 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 
 	switch(cmd) {
 	case LOOP_SET_STATUS:
-		err = mutex_lock_killable(&lo->lo_ctl_mutex);
-		if (!err) {
-			err = loop_set_status_compat(lo,
-						     (const struct compat_loop_info __user *)arg);
-			mutex_unlock(&lo->lo_ctl_mutex);
-		}
+		err = loop_set_status_compat(lo,
+			     (const struct compat_loop_info __user *)arg);
 		break;
 	case LOOP_GET_STATUS:
-		err = mutex_lock_killable(&lo->lo_ctl_mutex);
-		if (!err) {
-			err = loop_get_status_compat(lo,
-						     (struct compat_loop_info __user *)arg);
-			/* loop_get_status() unlocks lo_ctl_mutex */
-		}
+		err = loop_get_status_compat(lo,
+				     (struct compat_loop_info __user *)arg);
 		break;
 	case LOOP_SET_CAPACITY:
 	case LOOP_CLR_FD:
@@ -1625,9 +1717,11 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 static int lo_open(struct block_device *bdev, fmode_t mode)
 {
 	struct loop_device *lo;
-	int err = 0;
+	int err;
 
-	mutex_lock(&loop_index_mutex);
+	err = mutex_lock_killable(&loop_ctl_mutex);
+	if (err)
+		return err;
 	lo = bdev->bd_disk->private_data;
 	if (!lo) {
 		err = -ENXIO;
@@ -1636,26 +1730,30 @@ static int lo_open(struct block_device *bdev, fmode_t mode)
 
 	atomic_inc(&lo->lo_refcnt);
 out:
-	mutex_unlock(&loop_index_mutex);
+	mutex_unlock(&loop_ctl_mutex);
 	return err;
 }
 
-static void __lo_release(struct loop_device *lo)
+static void lo_release(struct gendisk *disk, fmode_t mode)
 {
-	int err;
+	struct loop_device *lo;
 
+	mutex_lock(&loop_ctl_mutex);
+	lo = disk->private_data;
 	if (atomic_dec_return(&lo->lo_refcnt))
-		return;
+		goto out_unlock;
 
-	mutex_lock(&lo->lo_ctl_mutex);
 	if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) {
+		if (lo->lo_state != Lo_bound)
+			goto out_unlock;
+		lo->lo_state = Lo_rundown;
+		mutex_unlock(&loop_ctl_mutex);
 		/*
 		 * In autoclear mode, stop the loop thread
 		 * and remove configuration after last close.
 		 */
-		err = loop_clr_fd(lo);
-		if (!err)
-			return;
+		__loop_clr_fd(lo, true);
+		return;
 	} else if (lo->lo_state == Lo_bound) {
 		/*
 		 * Otherwise keep thread (if running) and config,
@@ -1665,14 +1763,8 @@ static void __lo_release(struct loop_device *lo)
 		blk_mq_unfreeze_queue(lo->lo_queue);
 	}
 
-	mutex_unlock(&lo->lo_ctl_mutex);
-}
-
-static void lo_release(struct gendisk *disk, fmode_t mode)
-{
-	mutex_lock(&loop_index_mutex);
-	__lo_release(disk->private_data);
-	mutex_unlock(&loop_index_mutex);
+out_unlock:
+	mutex_unlock(&loop_ctl_mutex);
 }
 
 static const struct block_device_operations lo_fops = {
@@ -1711,10 +1803,10 @@ static int unregister_transfer_cb(int id, void *ptr, void *data)
 	struct loop_device *lo = ptr;
 	struct loop_func_table *xfer = data;
 
-	mutex_lock(&lo->lo_ctl_mutex);
+	mutex_lock(&loop_ctl_mutex);
 	if (lo->lo_encryption == xfer)
 		loop_release_xfer(lo);
-	mutex_unlock(&lo->lo_ctl_mutex);
+	mutex_unlock(&loop_ctl_mutex);
 	return 0;
 }
 
@@ -1895,7 +1987,6 @@ static int loop_add(struct loop_device **l, int i)
 	if (!part_shift)
 		disk->flags |= GENHD_FL_NO_PART_SCAN;
 	disk->flags |= GENHD_FL_EXT_DEVT;
-	mutex_init(&lo->lo_ctl_mutex);
 	atomic_set(&lo->lo_refcnt, 0);
 	lo->lo_number		= i;
 	spin_lock_init(&lo->lo_lock);
@@ -1974,7 +2065,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data)
 	struct kobject *kobj;
 	int err;
 
-	mutex_lock(&loop_index_mutex);
+	mutex_lock(&loop_ctl_mutex);
 	err = loop_lookup(&lo, MINOR(dev) >> part_shift);
 	if (err < 0)
 		err = loop_add(&lo, MINOR(dev) >> part_shift);
@@ -1982,7 +2073,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data)
 		kobj = NULL;
 	else
 		kobj = get_disk_and_module(lo->lo_disk);
-	mutex_unlock(&loop_index_mutex);
+	mutex_unlock(&loop_ctl_mutex);
 
 	*part = 0;
 	return kobj;
@@ -1992,9 +2083,13 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd,
 			       unsigned long parm)
 {
 	struct loop_device *lo;
-	int ret = -ENOSYS;
+	int ret;
+
+	ret = mutex_lock_killable(&loop_ctl_mutex);
+	if (ret)
+		return ret;
 
-	mutex_lock(&loop_index_mutex);
+	ret = -ENOSYS;
 	switch (cmd) {
 	case LOOP_CTL_ADD:
 		ret = loop_lookup(&lo, parm);
@@ -2008,21 +2103,15 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd,
 		ret = loop_lookup(&lo, parm);
 		if (ret < 0)
 			break;
-		ret = mutex_lock_killable(&lo->lo_ctl_mutex);
-		if (ret)
-			break;
 		if (lo->lo_state != Lo_unbound) {
 			ret = -EBUSY;
-			mutex_unlock(&lo->lo_ctl_mutex);
 			break;
 		}
 		if (atomic_read(&lo->lo_refcnt) > 0) {
 			ret = -EBUSY;
-			mutex_unlock(&lo->lo_ctl_mutex);
 			break;
 		}
 		lo->lo_disk->private_data = NULL;
-		mutex_unlock(&lo->lo_ctl_mutex);
 		idr_remove(&loop_index_idr, lo->lo_number);
 		loop_remove(lo);
 		break;
@@ -2032,7 +2121,7 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd,
 			break;
 		ret = loop_add(&lo, -1);
 	}
-	mutex_unlock(&loop_index_mutex);
+	mutex_unlock(&loop_ctl_mutex);
 
 	return ret;
 }
@@ -2116,10 +2205,10 @@ static int __init loop_init(void)
 				  THIS_MODULE, loop_probe, NULL, NULL);
 
 	/* pre-create number of devices given by config or max_loop */
-	mutex_lock(&loop_index_mutex);
+	mutex_lock(&loop_ctl_mutex);
 	for (i = 0; i < nr; i++)
 		loop_add(&lo, i);
-	mutex_unlock(&loop_index_mutex);
+	mutex_unlock(&loop_ctl_mutex);
 
 	printk(KERN_INFO "loop: module loaded\n");
 	return 0;
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 4d42c7af7de7..af75a5ee4094 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -54,7 +54,6 @@ struct loop_device {
 
 	spinlock_t		lo_lock;
 	int			lo_state;
-	struct mutex		lo_ctl_mutex;
 	struct kthread_worker	worker;
 	struct task_struct	*worker_task;
 	bool			use_dio;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 4d4d6129ff66..c964315c7b0b 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -288,9 +288,10 @@ static void nbd_size_update(struct nbd_device *nbd)
 	blk_queue_physical_block_size(nbd->disk->queue, config->blksize);
 	set_capacity(nbd->disk, config->bytesize >> 9);
 	if (bdev) {
-		if (bdev->bd_disk)
+		if (bdev->bd_disk) {
 			bd_set_size(bdev, config->bytesize);
-		else
+			set_blocksize(bdev, config->blksize);
+		} else
 			bdev->bd_invalidated = 1;
 		bdput(bdev);
 	}
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index caa98a7fe392..db330a0106b2 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -692,6 +692,7 @@ config CRYPTO_DEV_BCM_SPU
 	depends on ARCH_BCM_IPROC
 	depends on MAILBOX
 	default m
+	select CRYPTO_AUTHENC
 	select CRYPTO_DES
 	select CRYPTO_MD5
 	select CRYPTO_SHA1
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index 2d1f1db9f807..cd464637b0cb 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -2845,44 +2845,28 @@ static int aead_authenc_setkey(struct crypto_aead *cipher,
 	struct spu_hw *spu = &iproc_priv.spu;
 	struct iproc_ctx_s *ctx = crypto_aead_ctx(cipher);
 	struct crypto_tfm *tfm = crypto_aead_tfm(cipher);
-	struct rtattr *rta = (void *)key;
-	struct crypto_authenc_key_param *param;
-	const u8 *origkey = key;
-	const unsigned int origkeylen = keylen;
-
-	int ret = 0;
+	struct crypto_authenc_keys keys;
+	int ret;
 
 	flow_log("%s() aead:%p key:%p keylen:%u\n", __func__, cipher, key,
 		 keylen);
 	flow_dump("  key: ", key, keylen);
 
-	if (!RTA_OK(rta, keylen))
-		goto badkey;
-	if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM)
-		goto badkey;
-	if (RTA_PAYLOAD(rta) < sizeof(*param))
+	ret = crypto_authenc_extractkeys(&keys, key, keylen);
+	if (ret)
 		goto badkey;
 
-	param = RTA_DATA(rta);
-	ctx->enckeylen = be32_to_cpu(param->enckeylen);
-
-	key += RTA_ALIGN(rta->rta_len);
-	keylen -= RTA_ALIGN(rta->rta_len);
-
-	if (keylen < ctx->enckeylen)
-		goto badkey;
-	if (ctx->enckeylen > MAX_KEY_SIZE)
+	if (keys.enckeylen > MAX_KEY_SIZE ||
+	    keys.authkeylen > MAX_KEY_SIZE)
 		goto badkey;
 
-	ctx->authkeylen = keylen - ctx->enckeylen;
-
-	if (ctx->authkeylen > MAX_KEY_SIZE)
-		goto badkey;
+	ctx->enckeylen = keys.enckeylen;
+	ctx->authkeylen = keys.authkeylen;
 
-	memcpy(ctx->enckey, key + ctx->authkeylen, ctx->enckeylen);
+	memcpy(ctx->enckey, keys.enckey, keys.enckeylen);
 	/* May end up padding auth key. So make sure it's zeroed. */
 	memset(ctx->authkey, 0, sizeof(ctx->authkey));
-	memcpy(ctx->authkey, key, ctx->authkeylen);
+	memcpy(ctx->authkey, keys.authkey, keys.authkeylen);
 
 	switch (ctx->alg->cipher_info.alg) {
 	case CIPHER_ALG_DES:
@@ -2890,7 +2874,7 @@ static int aead_authenc_setkey(struct crypto_aead *cipher,
 			u32 tmp[DES_EXPKEY_WORDS];
 			u32 flags = CRYPTO_TFM_RES_WEAK_KEY;
 
-			if (des_ekey(tmp, key) == 0) {
+			if (des_ekey(tmp, keys.enckey) == 0) {
 				if (crypto_aead_get_flags(cipher) &
 				    CRYPTO_TFM_REQ_WEAK_KEY) {
 					crypto_aead_set_flags(cipher, flags);
@@ -2905,7 +2889,7 @@ static int aead_authenc_setkey(struct crypto_aead *cipher,
 		break;
 	case CIPHER_ALG_3DES:
 		if (ctx->enckeylen == (DES_KEY_SIZE * 3)) {
-			const u32 *K = (const u32 *)key;
+			const u32 *K = (const u32 *)keys.enckey;
 			u32 flags = CRYPTO_TFM_RES_BAD_KEY_SCHED;
 
 			if (!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
@@ -2956,9 +2940,7 @@ static int aead_authenc_setkey(struct crypto_aead *cipher,
 		ctx->fallback_cipher->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
 		ctx->fallback_cipher->base.crt_flags |=
 		    tfm->crt_flags & CRYPTO_TFM_REQ_MASK;
-		ret =
-		    crypto_aead_setkey(ctx->fallback_cipher, origkey,
-				       origkeylen);
+		ret = crypto_aead_setkey(ctx->fallback_cipher, key, keylen);
 		if (ret) {
 			flow_log("  fallback setkey() returned:%d\n", ret);
 			tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 46924affa0bd..212fd0b3b8dd 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -1071,13 +1071,16 @@ static int ahash_final_no_ctx(struct ahash_request *req)
 
 	desc = edesc->hw_desc;
 
-	state->buf_dma = dma_map_single(jrdev, buf, buflen, DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, state->buf_dma)) {
-		dev_err(jrdev, "unable to map src\n");
-		goto unmap;
-	}
+	if (buflen) {
+		state->buf_dma = dma_map_single(jrdev, buf, buflen,
+						DMA_TO_DEVICE);
+		if (dma_mapping_error(jrdev, state->buf_dma)) {
+			dev_err(jrdev, "unable to map src\n");
+			goto unmap;
+		}
 
-	append_seq_in_ptr(desc, state->buf_dma, buflen, 0);
+		append_seq_in_ptr(desc, state->buf_dma, buflen, 0);
+	}
 
 	edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result,
 						digestsize);
diff --git a/drivers/crypto/ccree/cc_aead.c b/drivers/crypto/ccree/cc_aead.c
index 01b82b82f8b8..5852d29ae2da 100644
--- a/drivers/crypto/ccree/cc_aead.c
+++ b/drivers/crypto/ccree/cc_aead.c
@@ -540,13 +540,12 @@ static int cc_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 			  unsigned int keylen)
 {
 	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
-	struct rtattr *rta = (struct rtattr *)key;
 	struct cc_crypto_req cc_req = {};
-	struct crypto_authenc_key_param *param;
 	struct cc_hw_desc desc[MAX_AEAD_SETKEY_SEQ];
-	int rc = -EINVAL;
 	unsigned int seq_len = 0;
 	struct device *dev = drvdata_to_dev(ctx->drvdata);
+	const u8 *enckey, *authkey;
+	int rc;
 
 	dev_dbg(dev, "Setting key in context @%p for %s. key=%p keylen=%u\n",
 		ctx, crypto_tfm_alg_name(crypto_aead_tfm(tfm)), key, keylen);
@@ -554,35 +553,33 @@ static int cc_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 	/* STAT_PHASE_0: Init and sanity checks */
 
 	if (ctx->auth_mode != DRV_HASH_NULL) { /* authenc() alg. */
-		if (!RTA_OK(rta, keylen))
-			goto badkey;
-		if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM)
-			goto badkey;
-		if (RTA_PAYLOAD(rta) < sizeof(*param))
-			goto badkey;
-		param = RTA_DATA(rta);
-		ctx->enc_keylen = be32_to_cpu(param->enckeylen);
-		key += RTA_ALIGN(rta->rta_len);
-		keylen -= RTA_ALIGN(rta->rta_len);
-		if (keylen < ctx->enc_keylen)
+		struct crypto_authenc_keys keys;
+
+		rc = crypto_authenc_extractkeys(&keys, key, keylen);
+		if (rc)
 			goto badkey;
-		ctx->auth_keylen = keylen - ctx->enc_keylen;
+		enckey = keys.enckey;
+		authkey = keys.authkey;
+		ctx->enc_keylen = keys.enckeylen;
+		ctx->auth_keylen = keys.authkeylen;
 
 		if (ctx->cipher_mode == DRV_CIPHER_CTR) {
 			/* the nonce is stored in bytes at end of key */
+			rc = -EINVAL;
 			if (ctx->enc_keylen <
 			    (AES_MIN_KEY_SIZE + CTR_RFC3686_NONCE_SIZE))
 				goto badkey;
 			/* Copy nonce from last 4 bytes in CTR key to
 			 *  first 4 bytes in CTR IV
 			 */
-			memcpy(ctx->ctr_nonce, key + ctx->auth_keylen +
-			       ctx->enc_keylen - CTR_RFC3686_NONCE_SIZE,
-			       CTR_RFC3686_NONCE_SIZE);
+			memcpy(ctx->ctr_nonce, enckey + ctx->enc_keylen -
+			       CTR_RFC3686_NONCE_SIZE, CTR_RFC3686_NONCE_SIZE);
 			/* Set CTR key size */
 			ctx->enc_keylen -= CTR_RFC3686_NONCE_SIZE;
 		}
 	} else { /* non-authenc - has just one key */
+		enckey = key;
+		authkey = NULL;
 		ctx->enc_keylen = keylen;
 		ctx->auth_keylen = 0;
 	}
@@ -594,13 +591,14 @@ static int cc_aead_setkey(struct crypto_aead *tfm, const u8 *key,
 	/* STAT_PHASE_1: Copy key to ctx */
 
 	/* Get key material */
-	memcpy(ctx->enckey, key + ctx->auth_keylen, ctx->enc_keylen);
+	memcpy(ctx->enckey, enckey, ctx->enc_keylen);
 	if (ctx->enc_keylen == 24)
 		memset(ctx->enckey + 24, 0, CC_AES_KEY_SIZE_MAX - 24);
 	if (ctx->auth_mode == DRV_HASH_XCBC_MAC) {
-		memcpy(ctx->auth_state.xcbc.xcbc_keys, key, ctx->auth_keylen);
+		memcpy(ctx->auth_state.xcbc.xcbc_keys, authkey,
+		       ctx->auth_keylen);
 	} else if (ctx->auth_mode != DRV_HASH_NULL) { /* HMAC */
-		rc = cc_get_plain_hmac_key(tfm, key, ctx->auth_keylen);
+		rc = cc_get_plain_hmac_key(tfm, authkey, ctx->auth_keylen);
 		if (rc)
 			goto badkey;
 	}
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 6988012deca4..f4f3e9a5851e 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -1361,23 +1361,18 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
 	int max_len = is_sec1 ? TALITOS1_MAX_DATA_LEN : TALITOS2_MAX_DATA_LEN;
-	void *err;
 
 	if (cryptlen + authsize > max_len) {
 		dev_err(dev, "length exceeds h/w max limit\n");
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (ivsize)
-		iv_dma = dma_map_single(dev, iv, ivsize, DMA_TO_DEVICE);
-
 	if (!dst || dst == src) {
 		src_len = assoclen + cryptlen + authsize;
 		src_nents = sg_nents_for_len(src, src_len);
 		if (src_nents < 0) {
 			dev_err(dev, "Invalid number of src SG.\n");
-			err = ERR_PTR(-EINVAL);
-			goto error_sg;
+			return ERR_PTR(-EINVAL);
 		}
 		src_nents = (src_nents == 1) ? 0 : src_nents;
 		dst_nents = dst ? src_nents : 0;
@@ -1387,16 +1382,14 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 		src_nents = sg_nents_for_len(src, src_len);
 		if (src_nents < 0) {
 			dev_err(dev, "Invalid number of src SG.\n");
-			err = ERR_PTR(-EINVAL);
-			goto error_sg;
+			return ERR_PTR(-EINVAL);
 		}
 		src_nents = (src_nents == 1) ? 0 : src_nents;
 		dst_len = assoclen + cryptlen + (encrypt ? authsize : 0);
 		dst_nents = sg_nents_for_len(dst, dst_len);
 		if (dst_nents < 0) {
 			dev_err(dev, "Invalid number of dst SG.\n");
-			err = ERR_PTR(-EINVAL);
-			goto error_sg;
+			return ERR_PTR(-EINVAL);
 		}
 		dst_nents = (dst_nents == 1) ? 0 : dst_nents;
 	}
@@ -1423,11 +1416,14 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 	/* if its a ahash, add space for a second desc next to the first one */
 	if (is_sec1 && !dst)
 		alloc_len += sizeof(struct talitos_desc);
+	alloc_len += ivsize;
 
 	edesc = kmalloc(alloc_len, GFP_DMA | flags);
-	if (!edesc) {
-		err = ERR_PTR(-ENOMEM);
-		goto error_sg;
+	if (!edesc)
+		return ERR_PTR(-ENOMEM);
+	if (ivsize) {
+		iv = memcpy(((u8 *)edesc) + alloc_len - ivsize, iv, ivsize);
+		iv_dma = dma_map_single(dev, iv, ivsize, DMA_TO_DEVICE);
 	}
 	memset(&edesc->desc, 0, sizeof(edesc->desc));
 
@@ -1445,10 +1441,6 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 						     DMA_BIDIRECTIONAL);
 	}
 	return edesc;
-error_sg:
-	if (iv_dma)
-		dma_unmap_single(dev, iv_dma, ivsize, DMA_TO_DEVICE);
-	return err;
 }
 
 static struct talitos_edesc *aead_edesc_alloc(struct aead_request *areq, u8 *iv,
diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
index d5b7f315098c..087470ad6436 100644
--- a/drivers/gpu/drm/drm_atomic_uapi.c
+++ b/drivers/gpu/drm/drm_atomic_uapi.c
@@ -1275,12 +1275,11 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
 			(arg->flags & DRM_MODE_PAGE_FLIP_EVENT))
 		return -EINVAL;
 
-	drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE);
-
 	state = drm_atomic_state_alloc(dev);
 	if (!state)
 		return -ENOMEM;
 
+	drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE);
 	state->acquire_ctx = &ctx;
 	state->allow_modeset = !!(arg->flags & DRM_MODE_ATOMIC_ALLOW_MODESET);
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index b10ed61526a5..6950e365135c 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1690,9 +1690,14 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 	struct drm_fb_helper *fb_helper = info->par;
 	struct drm_framebuffer *fb = fb_helper->fb;
 
-	if (var->pixclock != 0 || in_dbg_master())
+	if (in_dbg_master())
 		return -EINVAL;
 
+	if (var->pixclock != 0) {
+		DRM_DEBUG("fbdev emulation doesn't support changing the pixel clock, value of pixclock is ignored\n");
+		var->pixclock = 0;
+	}
+
 	/*
 	 * Changes struct fb_var_screeninfo are currently not pushed back
 	 * to KMS, hence fail if different settings are requested.
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index be8b754eaf60..9bc3654c1c7f 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/drivers/gpu/drm/drm_mode_object.c
@@ -458,11 +458,11 @@ static int set_property_atomic(struct drm_mode_object *obj,
 	struct drm_modeset_acquire_ctx ctx;
 	int ret;
 
-	drm_modeset_acquire_init(&ctx, 0);
-
 	state = drm_atomic_state_alloc(dev);
 	if (!state)
 		return -ENOMEM;
+
+	drm_modeset_acquire_init(&ctx, 0);
 	state->acquire_ctx = &ctx;
 retry:
 	if (prop == state->dev->mode_config.dpms_property) {
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index c1072143da1d..e70c450427dc 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -996,7 +996,7 @@ static int intel_vgpu_mmap(struct mdev_device *mdev, struct vm_area_struct *vma)
 {
 	unsigned int index;
 	u64 virtaddr;
-	unsigned long req_size, pgoff = 0;
+	unsigned long req_size, pgoff, req_start;
 	pgprot_t pg_prot;
 	struct intel_vgpu *vgpu = mdev_get_drvdata(mdev);
 
@@ -1014,7 +1014,17 @@ static int intel_vgpu_mmap(struct mdev_device *mdev, struct vm_area_struct *vma)
 	pg_prot = vma->vm_page_prot;
 	virtaddr = vma->vm_start;
 	req_size = vma->vm_end - vma->vm_start;
-	pgoff = vgpu_aperture_pa_base(vgpu) >> PAGE_SHIFT;
+	pgoff = vma->vm_pgoff &
+		((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
+	req_start = pgoff << PAGE_SHIFT;
+
+	if (!intel_vgpu_in_aperture(vgpu, req_start))
+		return -EINVAL;
+	if (req_start + req_size >
+	    vgpu_aperture_offset(vgpu) + vgpu_aperture_sz(vgpu))
+		return -EINVAL;
+
+	pgoff = (gvt_aperture_pa_base(vgpu->gvt) >> PAGE_SHIFT) + pgoff;
 
 	return remap_pfn_range(vma, virtaddr, pgoff, req_size, pg_prot);
 }
diff --git a/drivers/gpu/drm/rockchip/rockchip_rgb.c b/drivers/gpu/drm/rockchip/rockchip_rgb.c
index 96ac1458a59c..37f93022a106 100644
--- a/drivers/gpu/drm/rockchip/rockchip_rgb.c
+++ b/drivers/gpu/drm/rockchip/rockchip_rgb.c
@@ -113,8 +113,10 @@ struct rockchip_rgb *rockchip_rgb_init(struct device *dev,
 		child_count++;
 		ret = drm_of_find_panel_or_bridge(dev->of_node, 0, endpoint_id,
 						  &panel, &bridge);
-		if (!ret)
+		if (!ret) {
+			of_node_put(endpoint);
 			break;
+		}
 	}
 
 	of_node_put(port);
diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c
index 7041007396ae..e3bcea4b4891 100644
--- a/drivers/gpu/drm/vkms/vkms_plane.c
+++ b/drivers/gpu/drm/vkms/vkms_plane.c
@@ -23,8 +23,11 @@ vkms_plane_duplicate_state(struct drm_plane *plane)
 		return NULL;
 
 	crc_data = kzalloc(sizeof(*crc_data), GFP_KERNEL);
-	if (WARN_ON(!crc_data))
-		DRM_INFO("Couldn't allocate crc_data");
+	if (!crc_data) {
+		DRM_DEBUG_KMS("Couldn't allocate crc_data\n");
+		kfree(vkms_state);
+		return NULL;
+	}
 
 	vkms_state->crc_data = crc_data;
 
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 573399e3ccc1..ff6468e7fe79 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -580,10 +580,6 @@ static int fill_res_pd_entry(struct sk_buff *msg, struct netlink_callback *cb,
 	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_RES_USECNT,
 			      atomic_read(&pd->usecnt), RDMA_NLDEV_ATTR_PAD))
 		goto err;
-	if ((pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) &&
-	    nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY,
-			pd->unsafe_global_rkey))
-		goto err;
 
 	if (fill_res_name_pid(msg, res))
 		goto err;
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index 42b8685c997e..3c633ab58052 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -427,7 +427,40 @@ static inline enum ib_qp_state pvrdma_qp_state_to_ib(enum pvrdma_qp_state state)
 
 static inline enum pvrdma_wr_opcode ib_wr_opcode_to_pvrdma(enum ib_wr_opcode op)
 {
-	return (enum pvrdma_wr_opcode)op;
+	switch (op) {
+	case IB_WR_RDMA_WRITE:
+		return PVRDMA_WR_RDMA_WRITE;
+	case IB_WR_RDMA_WRITE_WITH_IMM:
+		return PVRDMA_WR_RDMA_WRITE_WITH_IMM;
+	case IB_WR_SEND:
+		return PVRDMA_WR_SEND;
+	case IB_WR_SEND_WITH_IMM:
+		return PVRDMA_WR_SEND_WITH_IMM;
+	case IB_WR_RDMA_READ:
+		return PVRDMA_WR_RDMA_READ;
+	case IB_WR_ATOMIC_CMP_AND_SWP:
+		return PVRDMA_WR_ATOMIC_CMP_AND_SWP;
+	case IB_WR_ATOMIC_FETCH_AND_ADD:
+		return PVRDMA_WR_ATOMIC_FETCH_AND_ADD;
+	case IB_WR_LSO:
+		return PVRDMA_WR_LSO;
+	case IB_WR_SEND_WITH_INV:
+		return PVRDMA_WR_SEND_WITH_INV;
+	case IB_WR_RDMA_READ_WITH_INV:
+		return PVRDMA_WR_RDMA_READ_WITH_INV;
+	case IB_WR_LOCAL_INV:
+		return PVRDMA_WR_LOCAL_INV;
+	case IB_WR_REG_MR:
+		return PVRDMA_WR_FAST_REG_MR;
+	case IB_WR_MASKED_ATOMIC_CMP_AND_SWP:
+		return PVRDMA_WR_MASKED_ATOMIC_CMP_AND_SWP;
+	case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD:
+		return PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD;
+	case IB_WR_REG_SIG_MR:
+		return PVRDMA_WR_REG_SIG_MR;
+	default:
+		return PVRDMA_WR_ERROR;
+	}
 }
 
 static inline enum ib_wc_status pvrdma_wc_status_to_ib(
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
index cf22f57a9f0d..418d9ab4ea7f 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
@@ -721,6 +721,12 @@ int pvrdma_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 		    wr->opcode == IB_WR_RDMA_WRITE_WITH_IMM)
 			wqe_hdr->ex.imm_data = wr->ex.imm_data;
 
+		if (unlikely(wqe_hdr->opcode == PVRDMA_WR_ERROR)) {
+			*bad_wr = wr;
+			ret = -EINVAL;
+			goto out;
+		}
+
 		switch (qp->ibqp.qp_type) {
 		case IB_QPT_GSI:
 		case IB_QPT_UD:
diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c
index 99f736c81286..fa77e2ae4ec4 100644
--- a/drivers/media/common/videobuf2/videobuf2-core.c
+++ b/drivers/media/common/videobuf2/videobuf2-core.c
@@ -2146,9 +2146,13 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma)
 			return -EINVAL;
 		}
 	}
+
+	mutex_lock(&q->mmap_lock);
+
 	if (vb2_fileio_is_active(q)) {
 		dprintk(1, "mmap: file io in progress\n");
-		return -EBUSY;
+		ret = -EBUSY;
+		goto unlock;
 	}
 
 	/*
@@ -2156,7 +2160,7 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma)
 	 */
 	ret = __find_plane_by_offset(q, off, &buffer, &plane);
 	if (ret)
-		return ret;
+		goto unlock;
 
 	vb = q->bufs[buffer];
 
@@ -2169,11 +2173,13 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma)
 	if (length < (vma->vm_end - vma->vm_start)) {
 		dprintk(1,
 			"MMAP invalid, as it would overflow buffer length\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto unlock;
 	}
 
-	mutex_lock(&q->mmap_lock);
 	ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma);
+
+unlock:
 	mutex_unlock(&q->mmap_lock);
 	if (ret)
 		return ret;
diff --git a/drivers/media/platform/vim2m.c b/drivers/media/platform/vim2m.c
index f938a2c54314..2d1ae83e2fde 100644
--- a/drivers/media/platform/vim2m.c
+++ b/drivers/media/platform/vim2m.c
@@ -809,7 +809,9 @@ static void vim2m_stop_streaming(struct vb2_queue *q)
 	struct vb2_v4l2_buffer *vbuf;
 	unsigned long flags;
 
-	cancel_delayed_work_sync(&dev->work_run);
+	if (v4l2_m2m_get_curr_priv(dev->m2m_dev) == ctx)
+		cancel_delayed_work_sync(&dev->work_run);
+
 	for (;;) {
 		if (V4L2_TYPE_IS_OUTPUT(q->type))
 			vbuf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.c b/drivers/media/platform/vivid/vivid-kthread-cap.c
index eebfff2126be..46e46e34a9e5 100644
--- a/drivers/media/platform/vivid/vivid-kthread-cap.c
+++ b/drivers/media/platform/vivid/vivid-kthread-cap.c
@@ -873,8 +873,11 @@ int vivid_start_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming)
 			"%s-vid-cap", dev->v4l2_dev.name);
 
 	if (IS_ERR(dev->kthread_vid_cap)) {
+		int err = PTR_ERR(dev->kthread_vid_cap);
+
+		dev->kthread_vid_cap = NULL;
 		v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n");
-		return PTR_ERR(dev->kthread_vid_cap);
+		return err;
 	}
 	*pstreaming = true;
 	vivid_grab_controls(dev, true);
diff --git a/drivers/media/platform/vivid/vivid-kthread-out.c b/drivers/media/platform/vivid/vivid-kthread-out.c
index 5a14810eeb69..ce5bcda2348c 100644
--- a/drivers/media/platform/vivid/vivid-kthread-out.c
+++ b/drivers/media/platform/vivid/vivid-kthread-out.c
@@ -244,8 +244,11 @@ int vivid_start_generating_vid_out(struct vivid_dev *dev, bool *pstreaming)
 			"%s-vid-out", dev->v4l2_dev.name);
 
 	if (IS_ERR(dev->kthread_vid_out)) {
+		int err = PTR_ERR(dev->kthread_vid_out);
+
+		dev->kthread_vid_out = NULL;
 		v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n");
-		return PTR_ERR(dev->kthread_vid_out);
+		return err;
 	}
 	*pstreaming = true;
 	vivid_grab_controls(dev, true);
diff --git a/drivers/media/platform/vivid/vivid-vid-common.c b/drivers/media/platform/vivid/vivid-vid-common.c
index 9645a91b8782..661f4015fba1 100644
--- a/drivers/media/platform/vivid/vivid-vid-common.c
+++ b/drivers/media/platform/vivid/vivid-vid-common.c
@@ -21,7 +21,7 @@ const struct v4l2_dv_timings_cap vivid_dv_timings_cap = {
 	.type = V4L2_DV_BT_656_1120,
 	/* keep this initialization for compatibility with GCC < 4.4.6 */
 	.reserved = { 0 },
-	V4L2_INIT_BT_TIMINGS(0, MAX_WIDTH, 0, MAX_HEIGHT, 14000000, 775000000,
+	V4L2_INIT_BT_TIMINGS(16, MAX_WIDTH, 16, MAX_HEIGHT, 14000000, 775000000,
 		V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT |
 		V4L2_DV_BT_STD_CVT | V4L2_DV_BT_STD_GTF,
 		V4L2_DV_BT_CAP_PROGRESSIVE | V4L2_DV_BT_CAP_INTERLACED)
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index c63746968fa3..3cdd09e4dd6b 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -286,6 +286,7 @@ static void v4l_print_format(const void *arg, bool write_only)
 	const struct v4l2_window *win;
 	const struct v4l2_sdr_format *sdr;
 	const struct v4l2_meta_format *meta;
+	u32 planes;
 	unsigned i;
 
 	pr_cont("type=%s", prt_names(p->type, v4l2_type_names));
@@ -316,7 +317,8 @@ static void v4l_print_format(const void *arg, bool write_only)
 			prt_names(mp->field, v4l2_field_names),
 			mp->colorspace, mp->num_planes, mp->flags,
 			mp->ycbcr_enc, mp->quantization, mp->xfer_func);
-		for (i = 0; i < mp->num_planes; i++)
+		planes = min_t(u32, mp->num_planes, VIDEO_MAX_PLANES);
+		for (i = 0; i < planes; i++)
 			printk(KERN_DEBUG "plane %u: bytesperline=%u sizeimage=%u\n", i,
 					mp->plane_fmt[i].bytesperline,
 					mp->plane_fmt[i].sizeimage);
diff --git a/drivers/mfd/tps6586x.c b/drivers/mfd/tps6586x.c
index b89379782741..9c7925ca13cf 100644
--- a/drivers/mfd/tps6586x.c
+++ b/drivers/mfd/tps6586x.c
@@ -592,6 +592,29 @@ static int tps6586x_i2c_remove(struct i2c_client *client)
 	return 0;
 }
 
+static int __maybe_unused tps6586x_i2c_suspend(struct device *dev)
+{
+	struct tps6586x *tps6586x = dev_get_drvdata(dev);
+
+	if (tps6586x->client->irq)
+		disable_irq(tps6586x->client->irq);
+
+	return 0;
+}
+
+static int __maybe_unused tps6586x_i2c_resume(struct device *dev)
+{
+	struct tps6586x *tps6586x = dev_get_drvdata(dev);
+
+	if (tps6586x->client->irq)
+		enable_irq(tps6586x->client->irq);
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(tps6586x_pm_ops, tps6586x_i2c_suspend,
+			 tps6586x_i2c_resume);
+
 static const struct i2c_device_id tps6586x_id_table[] = {
 	{ "tps6586x", 0 },
 	{ },
@@ -602,6 +625,7 @@ static struct i2c_driver tps6586x_driver = {
 	.driver	= {
 		.name	= "tps6586x",
 		.of_match_table = of_match_ptr(tps6586x_of_match),
+		.pm	= &tps6586x_pm_ops,
 	},
 	.probe		= tps6586x_i2c_probe,
 	.remove		= tps6586x_i2c_remove,
diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c
index 3633202e18f4..02a9aba85368 100644
--- a/drivers/misc/mic/vop/vop_main.c
+++ b/drivers/misc/mic/vop/vop_main.c
@@ -381,16 +381,21 @@ static int vop_find_vqs(struct virtio_device *dev, unsigned nvqs,
 	struct _vop_vdev *vdev = to_vopvdev(dev);
 	struct vop_device *vpdev = vdev->vpdev;
 	struct mic_device_ctrl __iomem *dc = vdev->dc;
-	int i, err, retry;
+	int i, err, retry, queue_idx = 0;
 
 	/* We must have this many virtqueues. */
 	if (nvqs > ioread8(&vdev->desc->num_vq))
 		return -ENOENT;
 
 	for (i = 0; i < nvqs; ++i) {
+		if (!names[i]) {
+			vqs[i] = NULL;
+			continue;
+		}
+
 		dev_dbg(_vop_dev(vdev), "%s: %d: %s\n",
 			__func__, i, names[i]);
-		vqs[i] = vop_find_vq(dev, i, callbacks[i], names[i],
+		vqs[i] = vop_find_vq(dev, queue_idx++, callbacks[i], names[i],
 				     ctx ? ctx[i] : false);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 3cc8bfee6c18..8594659cb592 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -258,6 +258,8 @@ struct sdhci_msm_host {
 	bool mci_removed;
 	const struct sdhci_msm_variant_ops *var_ops;
 	const struct sdhci_msm_offset *offset;
+	bool use_cdr;
+	u32 transfer_mode;
 };
 
 static const struct sdhci_msm_offset *sdhci_priv_msm_offset(struct sdhci_host *host)
@@ -1025,6 +1027,26 @@ out:
 	return ret;
 }
 
+static void sdhci_msm_set_cdr(struct sdhci_host *host, bool enable)
+{
+	const struct sdhci_msm_offset *msm_offset = sdhci_priv_msm_offset(host);
+	u32 config, oldconfig = readl_relaxed(host->ioaddr +
+					      msm_offset->core_dll_config);
+
+	config = oldconfig;
+	if (enable) {
+		config |= CORE_CDR_EN;
+		config &= ~CORE_CDR_EXT_EN;
+	} else {
+		config &= ~CORE_CDR_EN;
+		config |= CORE_CDR_EXT_EN;
+	}
+
+	if (config != oldconfig)
+		writel_relaxed(config, host->ioaddr +
+			       msm_offset->core_dll_config);
+}
+
 static int sdhci_msm_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
@@ -1042,8 +1064,14 @@ static int sdhci_msm_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	if (host->clock <= CORE_FREQ_100MHZ ||
 	    !(ios.timing == MMC_TIMING_MMC_HS400 ||
 	    ios.timing == MMC_TIMING_MMC_HS200 ||
-	    ios.timing == MMC_TIMING_UHS_SDR104))
+	    ios.timing == MMC_TIMING_UHS_SDR104)) {
+		msm_host->use_cdr = false;
+		sdhci_msm_set_cdr(host, false);
 		return 0;
+	}
+
+	/* Clock-Data-Recovery used to dynamically adjust RX sampling point */
+	msm_host->use_cdr = true;
 
 	/*
 	 * For HS400 tuning in HS200 timing requires:
@@ -1525,6 +1553,19 @@ static int __sdhci_msm_check_write(struct sdhci_host *host, u16 val, int reg)
 	case SDHCI_POWER_CONTROL:
 		req_type = !val ? REQ_BUS_OFF : REQ_BUS_ON;
 		break;
+	case SDHCI_TRANSFER_MODE:
+		msm_host->transfer_mode = val;
+		break;
+	case SDHCI_COMMAND:
+		if (!msm_host->use_cdr)
+			break;
+		if ((msm_host->transfer_mode & SDHCI_TRNS_READ) &&
+		    SDHCI_GET_CMD(val) != MMC_SEND_TUNING_BLOCK_HS200 &&
+		    SDHCI_GET_CMD(val) != MMC_SEND_TUNING_BLOCK)
+			sdhci_msm_set_cdr(host, true);
+		else
+			sdhci_msm_set_cdr(host, false);
+		break;
 	}
 
 	if (req_type) {
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 333387f1f1fe..62659abf73cd 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1948,6 +1948,9 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (!bond_has_slaves(bond)) {
 		bond_set_carrier(bond);
 		eth_hw_addr_random(bond_dev);
+		bond->nest_level = SINGLE_DEPTH_NESTING;
+	} else {
+		bond->nest_level = dev_get_nest_level(bond_dev) + 1;
 	}
 
 	unblock_netpoll_tx();
diff --git a/drivers/net/dsa/realtek-smi.c b/drivers/net/dsa/realtek-smi.c
index b4b839a1d095..ad41ec63cc9f 100644
--- a/drivers/net/dsa/realtek-smi.c
+++ b/drivers/net/dsa/realtek-smi.c
@@ -347,16 +347,17 @@ int realtek_smi_setup_mdio(struct realtek_smi *smi)
 	struct device_node *mdio_np;
 	int ret;
 
-	mdio_np = of_find_compatible_node(smi->dev->of_node, NULL,
-					  "realtek,smi-mdio");
+	mdio_np = of_get_compatible_child(smi->dev->of_node, "realtek,smi-mdio");
 	if (!mdio_np) {
 		dev_err(smi->dev, "no MDIO bus node\n");
 		return -ENODEV;
 	}
 
 	smi->slave_mii_bus = devm_mdiobus_alloc(smi->dev);
-	if (!smi->slave_mii_bus)
-		return -ENOMEM;
+	if (!smi->slave_mii_bus) {
+		ret = -ENOMEM;
+		goto err_put_node;
+	}
 	smi->slave_mii_bus->priv = smi;
 	smi->slave_mii_bus->name = "SMI slave MII";
 	smi->slave_mii_bus->read = realtek_smi_mdio_read;
@@ -371,10 +372,15 @@ int realtek_smi_setup_mdio(struct realtek_smi *smi)
 	if (ret) {
 		dev_err(smi->dev, "unable to register MDIO bus %s\n",
 			smi->slave_mii_bus->id);
-		of_node_put(mdio_np);
+		goto err_put_node;
 	}
 
 	return 0;
+
+err_put_node:
+	of_node_put(mdio_np);
+
+	return ret;
 }
 
 static int realtek_smi_probe(struct platform_device *pdev)
@@ -457,6 +463,8 @@ static int realtek_smi_remove(struct platform_device *pdev)
 	struct realtek_smi *smi = dev_get_drvdata(&pdev->dev);
 
 	dsa_unregister_switch(smi->ds);
+	if (smi->slave_mii_bus)
+		of_node_put(smi->slave_mii_bus->dev.of_node);
 	gpiod_set_value(smi->reset, 1);
 
 	return 0;
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 20c9377e99cb..1ce8b729929f 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -962,13 +962,10 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 
 		memset(&ksettings, 0, sizeof(ksettings));
 		phy_ethtool_get_link_ksettings(netdev, &ksettings);
-		local_advertisement = phy_read(phydev, MII_ADVERTISE);
-		if (local_advertisement < 0)
-			return;
-
-		remote_advertisement = phy_read(phydev, MII_LPA);
-		if (remote_advertisement < 0)
-			return;
+		local_advertisement =
+			ethtool_adv_to_mii_adv_t(phydev->advertising);
+		remote_advertisement =
+			ethtool_adv_to_mii_adv_t(phydev->lp_advertising);
 
 		lan743x_phy_update_flowcontrol(adapter,
 					       ksettings.base.duplex,
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 209566f8097b..78ea9639b622 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -714,6 +714,7 @@ module_param(use_dac, int, 0);
 MODULE_PARM_DESC(use_dac, "Enable PCI DAC. Unsafe on 32 bit PCI slot.");
 module_param_named(debug, debug.msg_enable, int, 0);
 MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., 16=all)");
+MODULE_SOFTDEP("pre: realtek");
 MODULE_LICENSE("GPL");
 MODULE_FIRMWARE(FIRMWARE_8168D_1);
 MODULE_FIRMWARE(FIRMWARE_8168D_2);
@@ -1728,11 +1729,13 @@ static bool rtl8169_reset_counters(struct rtl8169_private *tp)
 
 static bool rtl8169_update_counters(struct rtl8169_private *tp)
 {
+	u8 val = RTL_R8(tp, ChipCmd);
+
 	/*
 	 * Some chips are unable to dump tally counters when the receiver
-	 * is disabled.
+	 * is disabled. If 0xff chip may be in a PCI power-save state.
 	 */
-	if ((RTL_R8(tp, ChipCmd) & CmdRxEnb) == 0)
+	if (!(val & CmdRxEnb) || val == 0xff)
 		return true;
 
 	return rtl8169_do_counters(tp, CounterDump);
diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c
index f7ebdcff53e4..4d66e4bb904a 100644
--- a/drivers/net/phy/bcm87xx.c
+++ b/drivers/net/phy/bcm87xx.c
@@ -193,6 +193,7 @@ static struct phy_driver bcm87xx_driver[] = {
 	.phy_id		= PHY_ID_BCM8706,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Broadcom BCM8706",
+	.features	= PHY_10GBIT_FEC_FEATURES,
 	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm87xx_config_init,
 	.config_aneg	= bcm87xx_config_aneg,
@@ -205,6 +206,7 @@ static struct phy_driver bcm87xx_driver[] = {
 	.phy_id		= PHY_ID_BCM8727,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Broadcom BCM8727",
+	.features	= PHY_10GBIT_FEC_FEATURES,
 	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm87xx_config_init,
 	.config_aneg	= bcm87xx_config_aneg,
diff --git a/drivers/net/phy/cortina.c b/drivers/net/phy/cortina.c
index 8022cd317f62..1a4d04afb7f0 100644
--- a/drivers/net/phy/cortina.c
+++ b/drivers/net/phy/cortina.c
@@ -88,6 +88,7 @@ static struct phy_driver cortina_driver[] = {
 	.phy_id		= PHY_ID_CS4340,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Cortina CS4340",
+	.features       = PHY_10GBIT_FEATURES,
 	.config_init	= gen10g_config_init,
 	.config_aneg	= gen10g_config_aneg,
 	.read_status	= cortina_read_status,
diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c
index ddc2c5ea3787..6ace118502b9 100644
--- a/drivers/net/phy/meson-gxl.c
+++ b/drivers/net/phy/meson-gxl.c
@@ -233,6 +233,7 @@ static struct phy_driver meson_gxl_phy[] = {
 		.name		= "Meson GXL Internal PHY",
 		.features	= PHY_BASIC_FEATURES,
 		.flags		= PHY_IS_INTERNAL | PHY_HAS_INTERRUPT,
+		.soft_reset     = genphy_soft_reset,
 		.config_init	= meson_gxl_config_init,
 		.aneg_done      = genphy_aneg_done,
 		.read_status	= meson_gxl_read_status,
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 9265dea79412..51611c7a23d1 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1105,6 +1105,7 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id		= PHY_ID_KSZ8873MLL,
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ8873MLL Switch",
+	.features	= PHY_BASIC_FEATURES,
 	.config_init	= kszphy_config_init,
 	.config_aneg	= ksz8873mll_config_aneg,
 	.read_status	= ksz8873mll_read_status,
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 26c41ede54a4..fd051ae787cb 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -61,6 +61,9 @@ EXPORT_SYMBOL_GPL(phy_gbit_all_ports_features);
 __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init;
 EXPORT_SYMBOL_GPL(phy_10gbit_features);
 
+__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init;
+EXPORT_SYMBOL_GPL(phy_10gbit_fec_features);
+
 static const int phy_basic_ports_array[] = {
 	ETHTOOL_LINK_MODE_Autoneg_BIT,
 	ETHTOOL_LINK_MODE_TP_BIT,
@@ -102,6 +105,11 @@ static const int phy_10gbit_features_array[] = {
 	ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
 };
 
+const int phy_10gbit_fec_features_array[1] = {
+	ETHTOOL_LINK_MODE_10000baseR_FEC_BIT,
+};
+EXPORT_SYMBOL_GPL(phy_10gbit_fec_features_array);
+
 __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init;
 EXPORT_SYMBOL_GPL(phy_10gbit_full_features);
 
@@ -184,6 +192,10 @@ static void features_init(void)
 	linkmode_set_bit_array(phy_10gbit_full_features_array,
 			       ARRAY_SIZE(phy_10gbit_full_features_array),
 			       phy_10gbit_full_features);
+	/* 10G FEC only */
+	linkmode_set_bit_array(phy_10gbit_fec_features_array,
+			       ARRAY_SIZE(phy_10gbit_fec_features_array),
+			       phy_10gbit_fec_features);
 }
 
 void phy_device_free(struct phy_device *phydev)
diff --git a/drivers/net/phy/teranetics.c b/drivers/net/phy/teranetics.c
index 22f3bdd8206c..91247182bc52 100644
--- a/drivers/net/phy/teranetics.c
+++ b/drivers/net/phy/teranetics.c
@@ -80,6 +80,7 @@ static struct phy_driver teranetics_driver[] = {
 	.phy_id		= PHY_ID_TN2020,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Teranetics TN2020",
+	.features       = PHY_10GBIT_FEATURES,
 	.soft_reset	= gen10g_no_soft_reset,
 	.aneg_done	= teranetics_aneg_done,
 	.config_init    = gen10g_config_init,
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 005020042be9..6658658246d2 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -852,10 +852,6 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 		err = 0;
 	}
 
-	rcu_assign_pointer(tfile->tun, tun);
-	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
-	tun->numqueues++;
-
 	if (tfile->detached) {
 		tun_enable_queue(tfile);
 	} else {
@@ -872,6 +868,13 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 	 * refcnt.
 	 */
 
+	/* Publish tfile->tun and tun->tfiles only after we've fully
+	 * initialized tfile; otherwise we risk using half-initialized
+	 * object.
+	 */
+	rcu_assign_pointer(tfile->tun, tun);
+	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
+	tun->numqueues++;
 out:
 	return err;
 }
diff --git a/drivers/of/property.c b/drivers/of/property.c
index f46828e3b082..43720c2de138 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -806,6 +806,7 @@ struct device_node *of_graph_get_remote_node(const struct device_node *node,
 
 	if (!of_device_is_available(remote)) {
 		pr_debug("not available for remote node\n");
+		of_node_put(remote);
 		return NULL;
 	}
 
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index de21f620b882..21b22a150930 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -153,10 +153,15 @@ static int rproc_virtio_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 				 const bool * ctx,
 				 struct irq_affinity *desc)
 {
-	int i, ret;
+	int i, ret, queue_idx = 0;
 
 	for (i = 0; i < nvqs; ++i) {
-		vqs[i] = rp_find_vq(vdev, i, callbacks[i], names[i],
+		if (!names[i]) {
+			vqs[i] = NULL;
+			continue;
+		}
+
+		vqs[i] = rp_find_vq(vdev, queue_idx++, callbacks[i], names[i],
 				    ctx ? ctx[i] : false);
 		if (IS_ERR(vqs[i])) {
 			ret = PTR_ERR(vqs[i]);
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index c9c57b4a0b71..4e1bdd03d2aa 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -635,7 +635,7 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 {
 	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
 	unsigned long *indicatorp = NULL;
-	int ret, i;
+	int ret, i, queue_idx = 0;
 	struct ccw1 *ccw;
 
 	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
@@ -643,8 +643,14 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		return -ENOMEM;
 
 	for (i = 0; i < nvqs; ++i) {
-		vqs[i] = virtio_ccw_setup_vq(vdev, i, callbacks[i], names[i],
-					     ctx ? ctx[i] : false, ccw);
+		if (!names[i]) {
+			vqs[i] = NULL;
+			continue;
+		}
+
+		vqs[i] = virtio_ccw_setup_vq(vdev, queue_idx++, callbacks[i],
+					     names[i], ctx ? ctx[i] : false,
+					     ccw);
 		if (IS_ERR(vqs[i])) {
 			ret = PTR_ERR(vqs[i]);
 			vqs[i] = NULL;
diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c
index a2b4179bfdf7..7639df91b110 100644
--- a/drivers/scsi/scsi_pm.c
+++ b/drivers/scsi/scsi_pm.c
@@ -80,8 +80,22 @@ static int scsi_dev_type_resume(struct device *dev,
 
 	if (err == 0) {
 		pm_runtime_disable(dev);
-		pm_runtime_set_active(dev);
+		err = pm_runtime_set_active(dev);
 		pm_runtime_enable(dev);
+
+		/*
+		 * Forcibly set runtime PM status of request queue to "active"
+		 * to make sure we can again get requests from the queue
+		 * (see also blk_pm_peek_request()).
+		 *
+		 * The resume hook will correct runtime PM status of the disk.
+		 */
+		if (!err && scsi_is_sdev_device(dev)) {
+			struct scsi_device *sdev = to_scsi_device(dev);
+
+			if (sdev->request_queue->dev)
+				blk_set_runtime_active(sdev->request_queue);
+		}
 	}
 
 	return err;
@@ -140,16 +154,6 @@ static int scsi_bus_resume_common(struct device *dev,
 	else
 		fn = NULL;
 
-	/*
-	 * Forcibly set runtime PM status of request queue to "active" to
-	 * make sure we can again get requests from the queue (see also
-	 * blk_pm_peek_request()).
-	 *
-	 * The resume hook will correct runtime PM status of the disk.
-	 */
-	if (scsi_is_sdev_device(dev) && pm_runtime_suspended(dev))
-		blk_set_runtime_active(to_scsi_device(dev)->request_queue);
-
 	if (fn) {
 		async_schedule_domain(fn, dev, &scsi_sd_pm_domain);
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index bd0a5c694a97..ba4b8b3ce8cf 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -206,6 +206,12 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
 	sp = buffer_data[0] & 0x80 ? 1 : 0;
 	buffer_data[0] &= ~0x80;
 
+	/*
+	 * Ensure WP, DPOFUA, and RESERVED fields are cleared in
+	 * received mode parameter buffer before doing MODE SELECT.
+	 */
+	data.device_specific = 0;
+
 	if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT,
 			     SD_MAX_RETRIES, &data, &sshdr)) {
 		if (scsi_sense_valid(&sshdr))
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 687250ec8032..23c6fd238422 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1256,7 +1256,8 @@ static void tty_driver_remove_tty(struct tty_driver *driver, struct tty_struct *
 static int tty_reopen(struct tty_struct *tty)
 {
 	struct tty_driver *driver = tty->driver;
-	int retval;
+	struct tty_ldisc *ld;
+	int retval = 0;
 
 	if (driver->type == TTY_DRIVER_TYPE_PTY &&
 	    driver->subtype == PTY_TYPE_MASTER)
@@ -1268,14 +1269,21 @@ static int tty_reopen(struct tty_struct *tty)
 	if (test_bit(TTY_EXCLUSIVE, &tty->flags) && !capable(CAP_SYS_ADMIN))
 		return -EBUSY;
 
-	tty->count++;
+	ld = tty_ldisc_ref_wait(tty);
+	if (ld) {
+		tty_ldisc_deref(ld);
+	} else {
+		retval = tty_ldisc_lock(tty, 5 * HZ);
+		if (retval)
+			return retval;
 
-	if (tty->ldisc)
-		return 0;
+		if (!tty->ldisc)
+			retval = tty_ldisc_reinit(tty, tty->termios.c_line);
+		tty_ldisc_unlock(tty);
+	}
 
-	retval = tty_ldisc_reinit(tty, tty->termios.c_line);
-	if (retval)
-		tty->count--;
+	if (retval == 0)
+		tty->count++;
 
 	return retval;
 }
diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c
index 0c98d88f795a..b989ca26fc78 100644
--- a/drivers/tty/tty_ldsem.c
+++ b/drivers/tty/tty_ldsem.c
@@ -293,6 +293,16 @@ down_write_failed(struct ld_semaphore *sem, long count, long timeout)
 	if (!locked)
 		atomic_long_add_return(-LDSEM_WAIT_BIAS, &sem->count);
 	list_del(&waiter.list);
+
+	/*
+	 * In case of timeout, wake up every reader who gave the right of way
+	 * to writer. Prevent separation readers into two groups:
+	 * one that helds semaphore and another that sleeps.
+	 * (in case of no contention with a writer)
+	 */
+	if (!locked && list_empty(&sem->write_wait))
+		__ldsem_wake_readers(sem);
+
 	raw_spin_unlock_irq(&sem->wait_lock);
 
 	__set_current_state(TASK_RUNNING);
diff --git a/drivers/video/fbdev/offb.c b/drivers/video/fbdev/offb.c
index 31f769d67195..057d3cdef92e 100644
--- a/drivers/video/fbdev/offb.c
+++ b/drivers/video/fbdev/offb.c
@@ -318,28 +318,28 @@ static void __iomem *offb_map_reg(struct device_node *np, int index,
 }
 
 static void offb_init_palette_hacks(struct fb_info *info, struct device_node *dp,
-				    const char *name, unsigned long address)
+				    unsigned long address)
 {
 	struct offb_par *par = (struct offb_par *) info->par;
 
-	if (dp && !strncmp(name, "ATY,Rage128", 11)) {
+	if (of_node_name_prefix(dp, "ATY,Rage128")) {
 		par->cmap_adr = offb_map_reg(dp, 2, 0, 0x1fff);
 		if (par->cmap_adr)
 			par->cmap_type = cmap_r128;
-	} else if (dp && (!strncmp(name, "ATY,RageM3pA", 12)
-			  || !strncmp(name, "ATY,RageM3p12A", 14))) {
+	} else if (of_node_name_prefix(dp, "ATY,RageM3pA") ||
+		   of_node_name_prefix(dp, "ATY,RageM3p12A")) {
 		par->cmap_adr = offb_map_reg(dp, 2, 0, 0x1fff);
 		if (par->cmap_adr)
 			par->cmap_type = cmap_M3A;
-	} else if (dp && !strncmp(name, "ATY,RageM3pB", 12)) {
+	} else if (of_node_name_prefix(dp, "ATY,RageM3pB")) {
 		par->cmap_adr = offb_map_reg(dp, 2, 0, 0x1fff);
 		if (par->cmap_adr)
 			par->cmap_type = cmap_M3B;
-	} else if (dp && !strncmp(name, "ATY,Rage6", 9)) {
+	} else if (of_node_name_prefix(dp, "ATY,Rage6")) {
 		par->cmap_adr = offb_map_reg(dp, 1, 0, 0x1fff);
 		if (par->cmap_adr)
 			par->cmap_type = cmap_radeon;
-	} else if (!strncmp(name, "ATY,", 4)) {
+	} else if (of_node_name_prefix(dp, "ATY,")) {
 		unsigned long base = address & 0xff000000UL;
 		par->cmap_adr =
 			ioremap(base + 0x7ff000, 0x1000) + 0xcc0;
@@ -350,7 +350,7 @@ static void offb_init_palette_hacks(struct fb_info *info, struct device_node *dp
 		par->cmap_adr = offb_map_reg(dp, 0, 0x6000, 0x1000);
 		if (par->cmap_adr)
 			par->cmap_type = cmap_gxt2000;
-	} else if (dp && !strncmp(name, "vga,Display-", 12)) {
+	} else if (of_node_name_prefix(dp, "vga,Display-")) {
 		/* Look for AVIVO initialized by SLOF */
 		struct device_node *pciparent = of_get_parent(dp);
 		const u32 *vid, *did;
@@ -438,7 +438,7 @@ static void __init offb_init_fb(const char *name,
 
 	par->cmap_type = cmap_unknown;
 	if (depth == 8)
-		offb_init_palette_hacks(info, dp, name, address);
+		offb_init_palette_hacks(info, dp, address);
 	else
 		fix->visual = FB_VISUAL_TRUECOLOR;
 
diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
index a3edb20ea4c3..a846d32ee653 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
@@ -609,6 +609,8 @@ int omapfb_ioctl(struct fb_info *fbi, unsigned int cmd, unsigned long arg)
 
 	int r = 0;
 
+	memset(&p, 0, sizeof(p));
+
 	switch (cmd) {
 	case OMAPFB_SYNC_GFX:
 		DBG("ioctl SYNC_GFX\n");
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 728ecd1eea30..fb12fe205f86 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -61,6 +61,10 @@ enum virtio_balloon_vq {
 	VIRTIO_BALLOON_VQ_MAX
 };
 
+enum virtio_balloon_config_read {
+	VIRTIO_BALLOON_CONFIG_READ_CMD_ID = 0,
+};
+
 struct virtio_balloon {
 	struct virtio_device *vdev;
 	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq;
@@ -77,14 +81,20 @@ struct virtio_balloon {
 	/* Prevent updating balloon when it is being canceled. */
 	spinlock_t stop_update_lock;
 	bool stop_update;
+	/* Bitmap to indicate if reading the related config fields are needed */
+	unsigned long config_read_bitmap;
 
 	/* The list of allocated free pages, waiting to be given back to mm */
 	struct list_head free_page_list;
 	spinlock_t free_page_list_lock;
 	/* The number of free page blocks on the above list */
 	unsigned long num_free_page_blocks;
-	/* The cmd id received from host */
-	u32 cmd_id_received;
+	/*
+	 * The cmd id received from host.
+	 * Read it via virtio_balloon_cmd_id_received to get the latest value
+	 * sent from host.
+	 */
+	u32 cmd_id_received_cache;
 	/* The cmd id that is actively in use */
 	__virtio32 cmd_id_active;
 	/* Buffer to store the stop sign */
@@ -390,37 +400,31 @@ static unsigned long return_free_pages_to_mm(struct virtio_balloon *vb,
 	return num_returned;
 }
 
+static void virtio_balloon_queue_free_page_work(struct virtio_balloon *vb)
+{
+	if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+		return;
+
+	/* No need to queue the work if the bit was already set. */
+	if (test_and_set_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
+			     &vb->config_read_bitmap))
+		return;
+
+	queue_work(vb->balloon_wq, &vb->report_free_page_work);
+}
+
 static void virtballoon_changed(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb = vdev->priv;
 	unsigned long flags;
-	s64 diff = towards_target(vb);
-
-	if (diff) {
-		spin_lock_irqsave(&vb->stop_update_lock, flags);
-		if (!vb->stop_update)
-			queue_work(system_freezable_wq,
-				   &vb->update_balloon_size_work);
-		spin_unlock_irqrestore(&vb->stop_update_lock, flags);
-	}
 
-	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
-		virtio_cread(vdev, struct virtio_balloon_config,
-			     free_page_report_cmd_id, &vb->cmd_id_received);
-		if (vb->cmd_id_received == VIRTIO_BALLOON_CMD_ID_DONE) {
-			/* Pass ULONG_MAX to give back all the free pages */
-			return_free_pages_to_mm(vb, ULONG_MAX);
-		} else if (vb->cmd_id_received != VIRTIO_BALLOON_CMD_ID_STOP &&
-			   vb->cmd_id_received !=
-			   virtio32_to_cpu(vdev, vb->cmd_id_active)) {
-			spin_lock_irqsave(&vb->stop_update_lock, flags);
-			if (!vb->stop_update) {
-				queue_work(vb->balloon_wq,
-					   &vb->report_free_page_work);
-			}
-			spin_unlock_irqrestore(&vb->stop_update_lock, flags);
-		}
+	spin_lock_irqsave(&vb->stop_update_lock, flags);
+	if (!vb->stop_update) {
+		queue_work(system_freezable_wq,
+			   &vb->update_balloon_size_work);
+		virtio_balloon_queue_free_page_work(vb);
 	}
+	spin_unlock_irqrestore(&vb->stop_update_lock, flags);
 }
 
 static void update_balloon_size(struct virtio_balloon *vb)
@@ -527,6 +531,17 @@ static int init_vqs(struct virtio_balloon *vb)
 	return 0;
 }
 
+static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb)
+{
+	if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
+			       &vb->config_read_bitmap))
+		virtio_cread(vb->vdev, struct virtio_balloon_config,
+			     free_page_report_cmd_id,
+			     &vb->cmd_id_received_cache);
+
+	return vb->cmd_id_received_cache;
+}
+
 static int send_cmd_id_start(struct virtio_balloon *vb)
 {
 	struct scatterlist sg;
@@ -537,7 +552,8 @@ static int send_cmd_id_start(struct virtio_balloon *vb)
 	while (virtqueue_get_buf(vq, &unused))
 		;
 
-	vb->cmd_id_active = cpu_to_virtio32(vb->vdev, vb->cmd_id_received);
+	vb->cmd_id_active = virtio32_to_cpu(vb->vdev,
+					virtio_balloon_cmd_id_received(vb));
 	sg_init_one(&sg, &vb->cmd_id_active, sizeof(vb->cmd_id_active));
 	err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_active, GFP_KERNEL);
 	if (!err)
@@ -620,7 +636,8 @@ static int send_free_pages(struct virtio_balloon *vb)
 		 * stop the reporting.
 		 */
 		cmd_id_active = virtio32_to_cpu(vb->vdev, vb->cmd_id_active);
-		if (cmd_id_active != vb->cmd_id_received)
+		if (unlikely(cmd_id_active !=
+			     virtio_balloon_cmd_id_received(vb)))
 			break;
 
 		/*
@@ -637,11 +654,9 @@ static int send_free_pages(struct virtio_balloon *vb)
 	return 0;
 }
 
-static void report_free_page_func(struct work_struct *work)
+static void virtio_balloon_report_free_page(struct virtio_balloon *vb)
 {
 	int err;
-	struct virtio_balloon *vb = container_of(work, struct virtio_balloon,
-						 report_free_page_work);
 	struct device *dev = &vb->vdev->dev;
 
 	/* Start by sending the received cmd id to host with an outbuf. */
@@ -659,6 +674,23 @@ static void report_free_page_func(struct work_struct *work)
 		dev_err(dev, "Failed to send a stop id, err = %d\n", err);
 }
 
+static void report_free_page_func(struct work_struct *work)
+{
+	struct virtio_balloon *vb = container_of(work, struct virtio_balloon,
+						 report_free_page_work);
+	u32 cmd_id_received;
+
+	cmd_id_received = virtio_balloon_cmd_id_received(vb);
+	if (cmd_id_received == VIRTIO_BALLOON_CMD_ID_DONE) {
+		/* Pass ULONG_MAX to give back all the free pages */
+		return_free_pages_to_mm(vb, ULONG_MAX);
+	} else if (cmd_id_received != VIRTIO_BALLOON_CMD_ID_STOP &&
+		   cmd_id_received !=
+		   virtio32_to_cpu(vb->vdev, vb->cmd_id_active)) {
+		virtio_balloon_report_free_page(vb);
+	}
+}
+
 #ifdef CONFIG_BALLOON_COMPACTION
 /*
  * virtballoon_migratepage - perform the balloon page migration on behalf of
@@ -885,7 +917,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
 			goto out_del_vqs;
 		}
 		INIT_WORK(&vb->report_free_page_work, report_free_page_func);
-		vb->cmd_id_received = VIRTIO_BALLOON_CMD_ID_STOP;
+		vb->cmd_id_received_cache = VIRTIO_BALLOON_CMD_ID_STOP;
 		vb->cmd_id_active = cpu_to_virtio32(vb->vdev,
 						  VIRTIO_BALLOON_CMD_ID_STOP);
 		vb->cmd_id_stop = cpu_to_virtio32(vb->vdev,
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 4cd9ea5c75be..d9dd0f789279 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -468,7 +468,7 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 	unsigned int irq = platform_get_irq(vm_dev->pdev, 0);
-	int i, err;
+	int i, err, queue_idx = 0;
 
 	err = request_irq(irq, vm_interrupt, IRQF_SHARED,
 			dev_name(&vdev->dev), vm_dev);
@@ -476,7 +476,12 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		return err;
 
 	for (i = 0; i < nvqs; ++i) {
-		vqs[i] = vm_setup_vq(vdev, i, callbacks[i], names[i],
+		if (!names[i]) {
+			vqs[i] = NULL;
+			continue;
+		}
+
+		vqs[i] = vm_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
 				     ctx ? ctx[i] : false);
 		if (IS_ERR(vqs[i])) {
 			vm_del_vqs(vdev);
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 93194f3e7540..117e76b2f939 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -1650,7 +1650,7 @@ void xen_callback_vector(void)
 			xen_have_vector_callback = 0;
 			return;
 		}
-		pr_info("Xen HVM callback vector for event delivery is enabled\n");
+		pr_info_once("Xen HVM callback vector for event delivery is enabled\n");
 		alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR,
 				xen_hvm_callback_vector);
 	}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index a80b4f0ee7c4..5a35ed922c95 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -104,6 +104,20 @@ void invalidate_bdev(struct block_device *bdev)
 }
 EXPORT_SYMBOL(invalidate_bdev);
 
+static void set_init_blocksize(struct block_device *bdev)
+{
+	unsigned bsize = bdev_logical_block_size(bdev);
+	loff_t size = i_size_read(bdev->bd_inode);
+
+	while (bsize < PAGE_SIZE) {
+		if (size & bsize)
+			break;
+		bsize <<= 1;
+	}
+	bdev->bd_block_size = bsize;
+	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
+}
+
 int set_blocksize(struct block_device *bdev, int size)
 {
 	/* Size must be a power of two, and between 512 and PAGE_SIZE */
@@ -1408,18 +1422,9 @@ EXPORT_SYMBOL(check_disk_change);
 
 void bd_set_size(struct block_device *bdev, loff_t size)
 {
-	unsigned bsize = bdev_logical_block_size(bdev);
-
 	inode_lock(bdev->bd_inode);
 	i_size_write(bdev->bd_inode, size);
 	inode_unlock(bdev->bd_inode);
-	while (bsize < PAGE_SIZE) {
-		if (size & bsize)
-			break;
-		bsize <<= 1;
-	}
-	bdev->bd_block_size = bsize;
-	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
 }
 EXPORT_SYMBOL(bd_set_size);
 
@@ -1496,8 +1501,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				}
 			}
 
-			if (!ret)
+			if (!ret) {
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
+				set_init_blocksize(bdev);
+			}
 
 			/*
 			 * If the device is invalidated, rescan partition
@@ -1532,6 +1539,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				goto out_clear;
 			}
 			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
+			set_init_blocksize(bdev);
 		}
 
 		if (bdev->bd_bdi == &noop_backing_dev_info)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6d776717d8b3..f74c9e6b84ce 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4155,6 +4155,14 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info)
 		spin_lock(&fs_info->ordered_root_lock);
 	}
 	spin_unlock(&fs_info->ordered_root_lock);
+
+	/*
+	 * We need this here because if we've been flipped read-only we won't
+	 * get sync() from the umount, so we need to make sure any ordered
+	 * extents that haven't had their dirty pages IO start writeout yet
+	 * actually get run and error out properly.
+	 */
+	btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
 }
 
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 423281c19fad..02772f8823cf 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3147,9 +3147,6 @@ out:
 	/* once for the tree */
 	btrfs_put_ordered_extent(ordered_extent);
 
-	/* Try to release some metadata so we don't get an OOM but don't wait */
-	btrfs_btree_balance_dirty_nodelay(fs_info);
-
 	return ret;
 }
 
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index e02a9039b5ea..67bdbd3da52e 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -723,18 +723,15 @@ static int ramoops_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct ramoops_platform_data *pdata = dev->platform_data;
+	struct ramoops_platform_data pdata_local;
 	struct ramoops_context *cxt = &oops_cxt;
 	size_t dump_mem_sz;
 	phys_addr_t paddr;
 	int err = -EINVAL;
 
 	if (dev_of_node(dev) && !pdata) {
-		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-		if (!pdata) {
-			pr_err("cannot allocate platform data buffer\n");
-			err = -ENOMEM;
-			goto fail_out;
-		}
+		pdata = &pdata_local;
+		memset(pdata, 0, sizeof(*pdata));
 
 		err = ramoops_parse_dt(pdev, pdata);
 		if (err < 0)
diff --git a/include/linux/bcma/bcma_soc.h b/include/linux/bcma/bcma_soc.h
index 7cca5f859a90..f3c43519baa7 100644
--- a/include/linux/bcma/bcma_soc.h
+++ b/include/linux/bcma/bcma_soc.h
@@ -6,6 +6,7 @@
 
 struct bcma_soc {
 	struct bcma_bus bus;
+	struct device *dev;
 };
 
 int __init bcma_host_soc_register(struct bcma_soc *soc);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 70fc838e6773..0c5ee17b4d88 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -129,7 +129,7 @@ struct hd_struct {
 	struct disk_stats dkstats;
 #endif
 	struct percpu_ref ref;
-	struct rcu_head rcu_head;
+	struct rcu_work rcu_work;
 };
 
 #define GENHD_FL_REMOVABLE			1
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3ea87f774a76..306630d13523 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -48,6 +48,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init;
+extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init;
 
 #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features)
@@ -56,6 +57,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini
 #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features)
 #define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features)
 #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features)
+#define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features)
 #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features)
 
 /*
diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h
index 4b2b2baf8ab4..f32fc8289473 100644
--- a/include/net/netfilter/nf_conntrack_count.h
+++ b/include/net/netfilter/nf_conntrack_count.h
@@ -5,17 +5,10 @@
 
 struct nf_conncount_data;
 
-enum nf_conncount_list_add {
-	NF_CONNCOUNT_ADDED, 	/* list add was ok */
-	NF_CONNCOUNT_ERR,	/* -ENOMEM, must drop skb */
-	NF_CONNCOUNT_SKIP,	/* list is already reclaimed by gc */
-};
-
 struct nf_conncount_list {
 	spinlock_t list_lock;
 	struct list_head head;	/* connections with the same filtering key */
 	unsigned int count;	/* length of list */
-	bool dead;
 };
 
 struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family,
@@ -29,18 +22,12 @@ unsigned int nf_conncount_count(struct net *net,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_zone *zone);
 
-void nf_conncount_lookup(struct net *net, struct nf_conncount_list *list,
-			 const struct nf_conntrack_tuple *tuple,
-			 const struct nf_conntrack_zone *zone,
-			 bool *addit);
+int nf_conncount_add(struct net *net, struct nf_conncount_list *list,
+		     const struct nf_conntrack_tuple *tuple,
+		     const struct nf_conntrack_zone *zone);
 
 void nf_conncount_list_init(struct nf_conncount_list *list);
 
-enum nf_conncount_list_add
-nf_conncount_add(struct nf_conncount_list *list,
-		 const struct nf_conntrack_tuple *tuple,
-		 const struct nf_conntrack_zone *zone);
-
 bool nf_conncount_gc_list(struct net *net,
 			  struct nf_conncount_list *list);
 
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index f6052e70bf40..a55cb8b10165 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -268,7 +268,7 @@ struct sockaddr_in {
 #define	IN_MULTICAST(a)		IN_CLASSD(a)
 #define	IN_MULTICAST_NET	0xe0000000
 
-#define	IN_BADCLASS(a)		((((long int) (a) ) == 0xffffffff)
+#define	IN_BADCLASS(a)		(((long int) (a) ) == (long int)0xffffffff)
 #define	IN_EXPERIMENTAL(a)	IN_BADCLASS((a))
 
 #define	IN_CLASSE(a)		((((long int) (a)) & 0xf0000000) == 0xf0000000)
diff --git a/include/uapi/rdma/vmw_pvrdma-abi.h b/include/uapi/rdma/vmw_pvrdma-abi.h
index d13fd490b66d..6e73f0274e41 100644
--- a/include/uapi/rdma/vmw_pvrdma-abi.h
+++ b/include/uapi/rdma/vmw_pvrdma-abi.h
@@ -78,6 +78,7 @@ enum pvrdma_wr_opcode {
 	PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD,
 	PVRDMA_WR_BIND_MW,
 	PVRDMA_WR_REG_SIG_MR,
+	PVRDMA_WR_ERROR,
 };
 
 enum pvrdma_wc_status {
diff --git a/init/Kconfig b/init/Kconfig
index ed9352513c32..b902f9c89800 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1130,6 +1130,7 @@ config LD_DEAD_CODE_DATA_ELIMINATION
 	bool "Dead code and data elimination (EXPERIMENTAL)"
 	depends on HAVE_LD_DEAD_CODE_DATA_ELIMINATION
 	depends on EXPERT
+	depends on !(FUNCTION_TRACER && CC_IS_GCC && GCC_VERSION < 40800)
 	depends on $(cc-option,-ffunction-sections -fdata-sections)
 	depends on $(ld-option,--gc-sections)
 	help
diff --git a/lib/int_sqrt.c b/lib/int_sqrt.c
index 14436f4ca6bd..30e0f9770f88 100644
--- a/lib/int_sqrt.c
+++ b/lib/int_sqrt.c
@@ -52,7 +52,7 @@ u32 int_sqrt64(u64 x)
 	if (x <= ULONG_MAX)
 		return int_sqrt((unsigned long) x);
 
-	m = 1ULL << (fls64(x) & ~1ULL);
+	m = 1ULL << ((fls64(x) - 1) & ~1ULL);
 	while (m != 0) {
 		b = y + m;
 		y >>= 1;
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index b1b5e8516724..ed683e5b73ba 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -278,7 +278,7 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_
 		struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 		int ret;
 
-		if (neigh->hh.hh_len) {
+		if ((neigh->nud_state & NUD_CONNECTED) && neigh->hh.hh_len) {
 			neigh_hh_bridge(&neigh->hh, skb);
 			skb->dev = nf_bridge->physindev;
 			ret = br_handle_frame_finish(net, sk, skb);
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 491828713e0b..5e55cef0cec3 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1137,14 +1137,16 @@ static int do_replace(struct net *net, const void __user *user,
 	tmp.name[sizeof(tmp.name) - 1] = 0;
 
 	countersize = COUNTER_OFFSET(tmp.nentries) * nr_cpu_ids;
-	newinfo = vmalloc(sizeof(*newinfo) + countersize);
+	newinfo = __vmalloc(sizeof(*newinfo) + countersize, GFP_KERNEL_ACCOUNT,
+			    PAGE_KERNEL);
 	if (!newinfo)
 		return -ENOMEM;
 
 	if (countersize)
 		memset(newinfo->counters, 0, countersize);
 
-	newinfo->entries = vmalloc(tmp.entries_size);
+	newinfo->entries = __vmalloc(tmp.entries_size, GFP_KERNEL_ACCOUNT,
+				     PAGE_KERNEL);
 	if (!newinfo->entries) {
 		ret = -ENOMEM;
 		goto free_newinfo;
diff --git a/net/can/gw.c b/net/can/gw.c
index faa3da88a127..53859346dc9a 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -416,13 +416,29 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
 	while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx])
 		(*gwj->mod.modfunc[modidx++])(cf, &gwj->mod);
 
-	/* check for checksum updates when the CAN frame has been modified */
+	/* Has the CAN frame been modified? */
 	if (modidx) {
-		if (gwj->mod.csumfunc.crc8)
+		/* get available space for the processed CAN frame type */
+		int max_len = nskb->len - offsetof(struct can_frame, data);
+
+		/* dlc may have changed, make sure it fits to the CAN frame */
+		if (cf->can_dlc > max_len)
+			goto out_delete;
+
+		/* check for checksum updates in classic CAN length only */
+		if (gwj->mod.csumfunc.crc8) {
+			if (cf->can_dlc > 8)
+				goto out_delete;
+
 			(*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8);
+		}
+
+		if (gwj->mod.csumfunc.xor) {
+			if (cf->can_dlc > 8)
+				goto out_delete;
 
-		if (gwj->mod.csumfunc.xor)
 			(*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor);
+		}
 	}
 
 	/* clear the skb timestamp if not configured the other way */
@@ -434,6 +450,14 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
 		gwj->dropped_frames++;
 	else
 		gwj->handled_frames++;
+
+	return;
+
+ out_delete:
+	/* delete frame due to misconfiguration */
+	gwj->deleted_frames++;
+	kfree_skb(nskb);
+	return;
 }
 
 static inline int cgw_register_filter(struct net *net, struct cgw_job *gwj)
diff --git a/net/core/filter.c b/net/core/filter.c
index 8d2c629501e2..eb0007f30142 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2023,18 +2023,19 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
 static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev,
 				 u32 flags)
 {
-	/* skb->mac_len is not set on normal egress */
-	unsigned int mlen = skb->network_header - skb->mac_header;
+	unsigned int mlen = skb_network_offset(skb);
 
-	__skb_pull(skb, mlen);
+	if (mlen) {
+		__skb_pull(skb, mlen);
 
-	/* At ingress, the mac header has already been pulled once.
-	 * At egress, skb_pospull_rcsum has to be done in case that
-	 * the skb is originated from ingress (i.e. a forwarded skb)
-	 * to ensure that rcsum starts at net header.
-	 */
-	if (!skb_at_tc_ingress(skb))
-		skb_postpull_rcsum(skb, skb_mac_header(skb), mlen);
+		/* At ingress, the mac header has already been pulled once.
+		 * At egress, skb_pospull_rcsum has to be done in case that
+		 * the skb is originated from ingress (i.e. a forwarded skb)
+		 * to ensure that rcsum starts at net header.
+		 */
+		if (!skb_at_tc_ingress(skb))
+			skb_postpull_rcsum(skb, skb_mac_header(skb), mlen);
+	}
 	skb_pop_mac_header(skb);
 	skb_reset_mac_len(skb);
 	return flags & BPF_F_INGRESS ?
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 3e85437f7106..a648568c5e8f 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -63,6 +63,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 				     lwt->name ? : "<unknown>");
 			ret = BPF_OK;
 		} else {
+			skb_reset_mac_header(skb);
 			ret = skb_do_redirect(skb);
 			if (ret == 0)
 				ret = BPF_REDIRECT;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index fffcc130900e..82f341e84fae 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -148,19 +148,17 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
 
 static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
+	__be16 _ports[2], *ports;
 	struct sockaddr_in sin;
-	__be16 *ports;
-	int end;
-
-	end = skb_transport_offset(skb) + 4;
-	if (end > 0 && !pskb_may_pull(skb, end))
-		return;
 
 	/* All current transport protocols have the port numbers in the
 	 * first four bytes of the transport header and this function is
 	 * written with this assumption in mind.
 	 */
-	ports = (__be16 *)skb_transport_header(skb);
+	ports = skb_header_pointer(skb, skb_transport_offset(skb),
+				   sizeof(_ports), &_ports);
+	if (!ports)
+		return;
 
 	sin.sin_family = AF_INET;
 	sin.sin_addr.s_addr = ip_hdr(skb)->daddr;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index f87dbc78b6bc..71a29e9c0620 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -226,7 +226,7 @@ static int tcp_write_timeout(struct sock *sk)
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits) {
 			dst_negative_advice(sk);
-		} else if (!tp->syn_data && !tp->syn_fastopen) {
+		} else {
 			sk_rethink_txhash(sk);
 		}
 		retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 1ede7a16a0be..cb24850d2c7f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -341,6 +341,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info)
 	skb_reset_network_header(skb);
 	iph = ipv6_hdr(skb);
 	iph->daddr = fl6->daddr;
+	ip6_flow_hdr(iph, 0, 0);
 
 	serr = SKB_EXT_ERR(skb);
 	serr->ee.ee_errno = err;
@@ -700,17 +701,15 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 	}
 	if (np->rxopt.bits.rxorigdstaddr) {
 		struct sockaddr_in6 sin6;
-		__be16 *ports;
-		int end;
+		__be16 _ports[2], *ports;
 
-		end = skb_transport_offset(skb) + 4;
-		if (end <= 0 || pskb_may_pull(skb, end)) {
+		ports = skb_header_pointer(skb, skb_transport_offset(skb),
+					   sizeof(_ports), &_ports);
+		if (ports) {
 			/* All current transport protocols have the port numbers in the
 			 * first four bytes of the transport header and this function is
 			 * written with this assumption in mind.
 			 */
-			ports = (__be16 *)skb_transport_header(skb);
-
 			sin6.sin6_family = AF_INET6;
 			sin6.sin6_addr = ipv6_hdr(skb)->daddr;
 			sin6.sin6_port = ports[1];
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index c9c53ade55c3..6d14cbe443f8 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -421,10 +421,10 @@ static int icmp6_iif(const struct sk_buff *skb)
 static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 		       const struct in6_addr *force_saddr)
 {
-	struct net *net = dev_net(skb->dev);
 	struct inet6_dev *idev = NULL;
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct sock *sk;
+	struct net *net;
 	struct ipv6_pinfo *np;
 	const struct in6_addr *saddr = NULL;
 	struct dst_entry *dst;
@@ -435,12 +435,16 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	int iif = 0;
 	int addr_type = 0;
 	int len;
-	u32 mark = IP6_REPLY_MARK(net, skb->mark);
+	u32 mark;
 
 	if ((u8 *)hdr < skb->head ||
 	    (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb))
 		return;
 
+	if (!skb->dev)
+		return;
+	net = dev_net(skb->dev);
+	mark = IP6_REPLY_MARK(net, skb->mark);
 	/*
 	 *	Make sure we respect the rules
 	 *	i.e. RFC 1885 2.4(e)
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 9cd180bda092..7554c56b2e63 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -33,12 +33,6 @@
 
 #define CONNCOUNT_SLOTS		256U
 
-#ifdef CONFIG_LOCKDEP
-#define CONNCOUNT_LOCK_SLOTS	8U
-#else
-#define CONNCOUNT_LOCK_SLOTS	256U
-#endif
-
 #define CONNCOUNT_GC_MAX_NODES	8
 #define MAX_KEYLEN		5
 
@@ -49,8 +43,6 @@ struct nf_conncount_tuple {
 	struct nf_conntrack_zone	zone;
 	int				cpu;
 	u32				jiffies32;
-	bool				dead;
-	struct rcu_head			rcu_head;
 };
 
 struct nf_conncount_rb {
@@ -60,7 +52,7 @@ struct nf_conncount_rb {
 	struct rcu_head rcu_head;
 };
 
-static spinlock_t nf_conncount_locks[CONNCOUNT_LOCK_SLOTS] __cacheline_aligned_in_smp;
+static spinlock_t nf_conncount_locks[CONNCOUNT_SLOTS] __cacheline_aligned_in_smp;
 
 struct nf_conncount_data {
 	unsigned int keylen;
@@ -89,79 +81,25 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen)
 	return memcmp(a, b, klen * sizeof(u32));
 }
 
-enum nf_conncount_list_add
-nf_conncount_add(struct nf_conncount_list *list,
-		 const struct nf_conntrack_tuple *tuple,
-		 const struct nf_conntrack_zone *zone)
-{
-	struct nf_conncount_tuple *conn;
-
-	if (WARN_ON_ONCE(list->count > INT_MAX))
-		return NF_CONNCOUNT_ERR;
-
-	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
-	if (conn == NULL)
-		return NF_CONNCOUNT_ERR;
-
-	conn->tuple = *tuple;
-	conn->zone = *zone;
-	conn->cpu = raw_smp_processor_id();
-	conn->jiffies32 = (u32)jiffies;
-	conn->dead = false;
-	spin_lock_bh(&list->list_lock);
-	if (list->dead == true) {
-		kmem_cache_free(conncount_conn_cachep, conn);
-		spin_unlock_bh(&list->list_lock);
-		return NF_CONNCOUNT_SKIP;
-	}
-	list_add_tail(&conn->node, &list->head);
-	list->count++;
-	spin_unlock_bh(&list->list_lock);
-	return NF_CONNCOUNT_ADDED;
-}
-EXPORT_SYMBOL_GPL(nf_conncount_add);
-
-static void __conn_free(struct rcu_head *h)
-{
-	struct nf_conncount_tuple *conn;
-
-	conn = container_of(h, struct nf_conncount_tuple, rcu_head);
-	kmem_cache_free(conncount_conn_cachep, conn);
-}
-
-static bool conn_free(struct nf_conncount_list *list,
+static void conn_free(struct nf_conncount_list *list,
 		      struct nf_conncount_tuple *conn)
 {
-	bool free_entry = false;
-
-	spin_lock_bh(&list->list_lock);
-
-	if (conn->dead) {
-		spin_unlock_bh(&list->list_lock);
-		return free_entry;
-	}
+	lockdep_assert_held(&list->list_lock);
 
 	list->count--;
-	conn->dead = true;
-	list_del_rcu(&conn->node);
-	if (list->count == 0) {
-		list->dead = true;
-		free_entry = true;
-	}
+	list_del(&conn->node);
 
-	spin_unlock_bh(&list->list_lock);
-	call_rcu(&conn->rcu_head, __conn_free);
-	return free_entry;
+	kmem_cache_free(conncount_conn_cachep, conn);
 }
 
 static const struct nf_conntrack_tuple_hash *
 find_or_evict(struct net *net, struct nf_conncount_list *list,
-	      struct nf_conncount_tuple *conn, bool *free_entry)
+	      struct nf_conncount_tuple *conn)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	unsigned long a, b;
 	int cpu = raw_smp_processor_id();
-	__s32 age;
+	u32 age;
 
 	found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
 	if (found)
@@ -176,52 +114,45 @@ find_or_evict(struct net *net, struct nf_conncount_list *list,
 	 */
 	age = a - b;
 	if (conn->cpu == cpu || age >= 2) {
-		*free_entry = conn_free(list, conn);
+		conn_free(list, conn);
 		return ERR_PTR(-ENOENT);
 	}
 
 	return ERR_PTR(-EAGAIN);
 }
 
-void nf_conncount_lookup(struct net *net,
-			 struct nf_conncount_list *list,
-			 const struct nf_conntrack_tuple *tuple,
-			 const struct nf_conntrack_zone *zone,
-			 bool *addit)
+static int __nf_conncount_add(struct net *net,
+			      struct nf_conncount_list *list,
+			      const struct nf_conntrack_tuple *tuple,
+			      const struct nf_conntrack_zone *zone)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	struct nf_conncount_tuple *conn, *conn_n;
 	struct nf_conn *found_ct;
 	unsigned int collect = 0;
-	bool free_entry = false;
-
-	/* best effort only */
-	*addit = tuple ? true : false;
 
 	/* check the saved connections */
 	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
 		if (collect > CONNCOUNT_GC_MAX_NODES)
 			break;
 
-		found = find_or_evict(net, list, conn, &free_entry);
+		found = find_or_evict(net, list, conn);
 		if (IS_ERR(found)) {
 			/* Not found, but might be about to be confirmed */
 			if (PTR_ERR(found) == -EAGAIN) {
-				if (!tuple)
-					continue;
-
 				if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
 				    nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
 				    nf_ct_zone_id(zone, zone->dir))
-					*addit = false;
-			} else if (PTR_ERR(found) == -ENOENT)
+					return 0; /* already exists */
+			} else {
 				collect++;
+			}
 			continue;
 		}
 
 		found_ct = nf_ct_tuplehash_to_ctrack(found);
 
-		if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple) &&
+		if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
 		    nf_ct_zone_equal(found_ct, zone, zone->dir)) {
 			/*
 			 * We should not see tuples twice unless someone hooks
@@ -229,7 +160,8 @@ void nf_conncount_lookup(struct net *net,
 			 *
 			 * Attempt to avoid a re-add in this case.
 			 */
-			*addit = false;
+			nf_ct_put(found_ct);
+			return 0;
 		} else if (already_closed(found_ct)) {
 			/*
 			 * we do not care about connections which are
@@ -243,19 +175,48 @@ void nf_conncount_lookup(struct net *net,
 
 		nf_ct_put(found_ct);
 	}
+
+	if (WARN_ON_ONCE(list->count > INT_MAX))
+		return -EOVERFLOW;
+
+	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
+	if (conn == NULL)
+		return -ENOMEM;
+
+	conn->tuple = *tuple;
+	conn->zone = *zone;
+	conn->cpu = raw_smp_processor_id();
+	conn->jiffies32 = (u32)jiffies;
+	list_add_tail(&conn->node, &list->head);
+	list->count++;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(nf_conncount_lookup);
+
+int nf_conncount_add(struct net *net,
+		     struct nf_conncount_list *list,
+		     const struct nf_conntrack_tuple *tuple,
+		     const struct nf_conntrack_zone *zone)
+{
+	int ret;
+
+	/* check the saved connections */
+	spin_lock_bh(&list->list_lock);
+	ret = __nf_conncount_add(net, list, tuple, zone);
+	spin_unlock_bh(&list->list_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_conncount_add);
 
 void nf_conncount_list_init(struct nf_conncount_list *list)
 {
 	spin_lock_init(&list->list_lock);
 	INIT_LIST_HEAD(&list->head);
 	list->count = 0;
-	list->dead = false;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_list_init);
 
-/* Return true if the list is empty */
+/* Return true if the list is empty. Must be called with BH disabled. */
 bool nf_conncount_gc_list(struct net *net,
 			  struct nf_conncount_list *list)
 {
@@ -263,17 +224,17 @@ bool nf_conncount_gc_list(struct net *net,
 	struct nf_conncount_tuple *conn, *conn_n;
 	struct nf_conn *found_ct;
 	unsigned int collected = 0;
-	bool free_entry = false;
 	bool ret = false;
 
+	/* don't bother if other cpu is already doing GC */
+	if (!spin_trylock(&list->list_lock))
+		return false;
+
 	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
-		found = find_or_evict(net, list, conn, &free_entry);
+		found = find_or_evict(net, list, conn);
 		if (IS_ERR(found)) {
-			if (PTR_ERR(found) == -ENOENT)  {
-				if (free_entry)
-					return true;
+			if (PTR_ERR(found) == -ENOENT)
 				collected++;
-			}
 			continue;
 		}
 
@@ -284,23 +245,19 @@ bool nf_conncount_gc_list(struct net *net,
 			 * closed already -> ditch it
 			 */
 			nf_ct_put(found_ct);
-			if (conn_free(list, conn))
-				return true;
+			conn_free(list, conn);
 			collected++;
 			continue;
 		}
 
 		nf_ct_put(found_ct);
 		if (collected > CONNCOUNT_GC_MAX_NODES)
-			return false;
+			break;
 	}
 
-	spin_lock_bh(&list->list_lock);
-	if (!list->count) {
-		list->dead = true;
+	if (!list->count)
 		ret = true;
-	}
-	spin_unlock_bh(&list->list_lock);
+	spin_unlock(&list->list_lock);
 
 	return ret;
 }
@@ -314,6 +271,7 @@ static void __tree_nodes_free(struct rcu_head *h)
 	kmem_cache_free(conncount_rb_cachep, rbconn);
 }
 
+/* caller must hold tree nf_conncount_locks[] lock */
 static void tree_nodes_free(struct rb_root *root,
 			    struct nf_conncount_rb *gc_nodes[],
 			    unsigned int gc_count)
@@ -323,8 +281,10 @@ static void tree_nodes_free(struct rb_root *root,
 	while (gc_count) {
 		rbconn = gc_nodes[--gc_count];
 		spin_lock(&rbconn->list.list_lock);
-		rb_erase(&rbconn->node, root);
-		call_rcu(&rbconn->rcu_head, __tree_nodes_free);
+		if (!rbconn->list.count) {
+			rb_erase(&rbconn->node, root);
+			call_rcu(&rbconn->rcu_head, __tree_nodes_free);
+		}
 		spin_unlock(&rbconn->list.list_lock);
 	}
 }
@@ -341,20 +301,19 @@ insert_tree(struct net *net,
 	    struct rb_root *root,
 	    unsigned int hash,
 	    const u32 *key,
-	    u8 keylen,
 	    const struct nf_conntrack_tuple *tuple,
 	    const struct nf_conntrack_zone *zone)
 {
-	enum nf_conncount_list_add ret;
 	struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES];
 	struct rb_node **rbnode, *parent;
 	struct nf_conncount_rb *rbconn;
 	struct nf_conncount_tuple *conn;
 	unsigned int count = 0, gc_count = 0;
-	bool node_found = false;
-
-	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+	u8 keylen = data->keylen;
+	bool do_gc = true;
 
+	spin_lock_bh(&nf_conncount_locks[hash]);
+restart:
 	parent = NULL;
 	rbnode = &(root->rb_node);
 	while (*rbnode) {
@@ -368,45 +327,32 @@ insert_tree(struct net *net,
 		} else if (diff > 0) {
 			rbnode = &((*rbnode)->rb_right);
 		} else {
-			/* unlikely: other cpu added node already */
-			node_found = true;
-			ret = nf_conncount_add(&rbconn->list, tuple, zone);
-			if (ret == NF_CONNCOUNT_ERR) {
+			int ret;
+
+			ret = nf_conncount_add(net, &rbconn->list, tuple, zone);
+			if (ret)
 				count = 0; /* hotdrop */
-			} else if (ret == NF_CONNCOUNT_ADDED) {
+			else
 				count = rbconn->list.count;
-			} else {
-				/* NF_CONNCOUNT_SKIP, rbconn is already
-				 * reclaimed by gc, insert a new tree node
-				 */
-				node_found = false;
-			}
-			break;
+			tree_nodes_free(root, gc_nodes, gc_count);
+			goto out_unlock;
 		}
 
 		if (gc_count >= ARRAY_SIZE(gc_nodes))
 			continue;
 
-		if (nf_conncount_gc_list(net, &rbconn->list))
+		if (do_gc && nf_conncount_gc_list(net, &rbconn->list))
 			gc_nodes[gc_count++] = rbconn;
 	}
 
 	if (gc_count) {
 		tree_nodes_free(root, gc_nodes, gc_count);
-		/* tree_node_free before new allocation permits
-		 * allocator to re-use newly free'd object.
-		 *
-		 * This is a rare event; in most cases we will find
-		 * existing node to re-use. (or gc_count is 0).
-		 */
-
-		if (gc_count >= ARRAY_SIZE(gc_nodes))
-			schedule_gc_worker(data, hash);
+		schedule_gc_worker(data, hash);
+		gc_count = 0;
+		do_gc = false;
+		goto restart;
 	}
 
-	if (node_found)
-		goto out_unlock;
-
 	/* expected case: match, insert new node */
 	rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC);
 	if (rbconn == NULL)
@@ -430,7 +376,7 @@ insert_tree(struct net *net,
 	rb_link_node_rcu(&rbconn->node, parent, rbnode);
 	rb_insert_color(&rbconn->node, root);
 out_unlock:
-	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+	spin_unlock_bh(&nf_conncount_locks[hash]);
 	return count;
 }
 
@@ -441,7 +387,6 @@ count_tree(struct net *net,
 	   const struct nf_conntrack_tuple *tuple,
 	   const struct nf_conntrack_zone *zone)
 {
-	enum nf_conncount_list_add ret;
 	struct rb_root *root;
 	struct rb_node *parent;
 	struct nf_conncount_rb *rbconn;
@@ -454,7 +399,6 @@ count_tree(struct net *net,
 	parent = rcu_dereference_raw(root->rb_node);
 	while (parent) {
 		int diff;
-		bool addit;
 
 		rbconn = rb_entry(parent, struct nf_conncount_rb, node);
 
@@ -464,31 +408,36 @@ count_tree(struct net *net,
 		} else if (diff > 0) {
 			parent = rcu_dereference_raw(parent->rb_right);
 		} else {
-			/* same source network -> be counted! */
-			nf_conncount_lookup(net, &rbconn->list, tuple, zone,
-					    &addit);
+			int ret;
 
-			if (!addit)
+			if (!tuple) {
+				nf_conncount_gc_list(net, &rbconn->list);
 				return rbconn->list.count;
+			}
 
-			ret = nf_conncount_add(&rbconn->list, tuple, zone);
-			if (ret == NF_CONNCOUNT_ERR) {
-				return 0; /* hotdrop */
-			} else if (ret == NF_CONNCOUNT_ADDED) {
-				return rbconn->list.count;
-			} else {
-				/* NF_CONNCOUNT_SKIP, rbconn is already
-				 * reclaimed by gc, insert a new tree node
-				 */
+			spin_lock_bh(&rbconn->list.list_lock);
+			/* Node might be about to be free'd.
+			 * We need to defer to insert_tree() in this case.
+			 */
+			if (rbconn->list.count == 0) {
+				spin_unlock_bh(&rbconn->list.list_lock);
 				break;
 			}
+
+			/* same source network -> be counted! */
+			ret = __nf_conncount_add(net, &rbconn->list, tuple, zone);
+			spin_unlock_bh(&rbconn->list.list_lock);
+			if (ret)
+				return 0; /* hotdrop */
+			else
+				return rbconn->list.count;
 		}
 	}
 
 	if (!tuple)
 		return 0;
 
-	return insert_tree(net, data, root, hash, key, keylen, tuple, zone);
+	return insert_tree(net, data, root, hash, key, tuple, zone);
 }
 
 static void tree_gc_worker(struct work_struct *work)
@@ -499,27 +448,47 @@ static void tree_gc_worker(struct work_struct *work)
 	struct rb_node *node;
 	unsigned int tree, next_tree, gc_count = 0;
 
-	tree = data->gc_tree % CONNCOUNT_LOCK_SLOTS;
+	tree = data->gc_tree % CONNCOUNT_SLOTS;
 	root = &data->root[tree];
 
+	local_bh_disable();
 	rcu_read_lock();
 	for (node = rb_first(root); node != NULL; node = rb_next(node)) {
 		rbconn = rb_entry(node, struct nf_conncount_rb, node);
 		if (nf_conncount_gc_list(data->net, &rbconn->list))
-			gc_nodes[gc_count++] = rbconn;
+			gc_count++;
 	}
 	rcu_read_unlock();
+	local_bh_enable();
+
+	cond_resched();
 
 	spin_lock_bh(&nf_conncount_locks[tree]);
+	if (gc_count < ARRAY_SIZE(gc_nodes))
+		goto next; /* do not bother */
 
-	if (gc_count) {
-		tree_nodes_free(root, gc_nodes, gc_count);
+	gc_count = 0;
+	node = rb_first(root);
+	while (node != NULL) {
+		rbconn = rb_entry(node, struct nf_conncount_rb, node);
+		node = rb_next(node);
+
+		if (rbconn->list.count > 0)
+			continue;
+
+		gc_nodes[gc_count++] = rbconn;
+		if (gc_count >= ARRAY_SIZE(gc_nodes)) {
+			tree_nodes_free(root, gc_nodes, gc_count);
+			gc_count = 0;
+		}
 	}
 
+	tree_nodes_free(root, gc_nodes, gc_count);
+next:
 	clear_bit(tree, data->pending_trees);
 
 	next_tree = (tree + 1) % CONNCOUNT_SLOTS;
-	next_tree = find_next_bit(data->pending_trees, next_tree, CONNCOUNT_SLOTS);
+	next_tree = find_next_bit(data->pending_trees, CONNCOUNT_SLOTS, next_tree);
 
 	if (next_tree < CONNCOUNT_SLOTS) {
 		data->gc_tree = next_tree;
@@ -621,10 +590,7 @@ static int __init nf_conncount_modinit(void)
 {
 	int i;
 
-	BUILD_BUG_ON(CONNCOUNT_LOCK_SLOTS > CONNCOUNT_SLOTS);
-	BUILD_BUG_ON((CONNCOUNT_SLOTS % CONNCOUNT_LOCK_SLOTS) != 0);
-
-	for (i = 0; i < CONNCOUNT_LOCK_SLOTS; ++i)
+	for (i = 0; i < CONNCOUNT_SLOTS; ++i)
 		spin_lock_init(&nf_conncount_locks[i]);
 
 	conncount_conn_cachep = kmem_cache_create("nf_conncount_tuple",
diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c
index b90d96ba4a12..af1497ab9464 100644
--- a/net/netfilter/nft_connlimit.c
+++ b/net/netfilter/nft_connlimit.c
@@ -30,7 +30,6 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 	enum ip_conntrack_info ctinfo;
 	const struct nf_conn *ct;
 	unsigned int count;
-	bool addit;
 
 	tuple_ptr = &tuple;
 
@@ -44,19 +43,12 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 		return;
 	}
 
-	nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone,
-			    &addit);
-	count = priv->list.count;
-
-	if (!addit)
-		goto out;
-
-	if (nf_conncount_add(&priv->list, tuple_ptr, zone) == NF_CONNCOUNT_ERR) {
+	if (nf_conncount_add(nft_net(pkt), &priv->list, tuple_ptr, zone)) {
 		regs->verdict.code = NF_DROP;
 		return;
 	}
-	count++;
-out:
+
+	count = priv->list.count;
 
 	if ((count > priv->limit) ^ priv->invert) {
 		regs->verdict.code = NFT_BREAK;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index eedacdebcd4c..d0945253f43b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2628,7 +2628,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out;
+			goto out_put;
 	}
 
 	err = -ENXIO;
@@ -2828,7 +2828,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out;
+			goto out_unlock;
 	}
 
 	err = -ENXIO;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 7f0539db5604..0bae07e9c9e7 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -97,11 +97,9 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
 
 	switch (ev) {
 	case NETDEV_UP:
-		addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
+		addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
 		if (addr) {
 			addr->a.v6.sin6_family = AF_INET6;
-			addr->a.v6.sin6_port = 0;
-			addr->a.v6.sin6_flowinfo = 0;
 			addr->a.v6.sin6_addr = ifa->addr;
 			addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex;
 			addr->valid = 1;
@@ -431,7 +429,6 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist,
 		addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
 		if (addr) {
 			addr->a.v6.sin6_family = AF_INET6;
-			addr->a.v6.sin6_port = 0;
 			addr->a.v6.sin6_addr = ifp->addr;
 			addr->a.v6.sin6_scope_id = dev->ifindex;
 			addr->valid = 1;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 9b277bd36d1a..85af878f5668 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -101,7 +101,6 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist,
 		addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
 		if (addr) {
 			addr->a.v4.sin_family = AF_INET;
-			addr->a.v4.sin_port = 0;
 			addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
 			addr->valid = 1;
 			INIT_LIST_HEAD(&addr->list);
@@ -776,10 +775,9 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
 
 	switch (ev) {
 	case NETDEV_UP:
-		addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
+		addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
 		if (addr) {
 			addr->a.v4.sin_family = AF_INET;
-			addr->a.v4.sin_port = 0;
 			addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
 			addr->valid = 1;
 			spin_lock_bh(&net->sctp.local_addr_lock);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 82cb0e5634bc..5d2214183601 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -146,6 +146,9 @@ static int smc_release(struct socket *sock)
 		sock_set_flag(sk, SOCK_DEAD);
 		sk->sk_shutdown |= SHUTDOWN_MASK;
 	}
+
+	sk->sk_prot->unhash(sk);
+
 	if (smc->clcsock) {
 		if (smc->use_fallback && sk->sk_state == SMC_LISTEN) {
 			/* wake up clcsock accept */
@@ -170,7 +173,6 @@ static int smc_release(struct socket *sock)
 		smc_conn_free(&smc->conn);
 	release_sock(sk);
 
-	sk->sk_prot->unhash(sk);
 	sock_put(sk); /* final sock_put */
 out:
 	return rc;
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index c7872bc13860..08b5fa4a2852 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -771,6 +771,12 @@ void rpcb_getport_async(struct rpc_task *task)
 	case RPCBVERS_3:
 		map->r_netid = xprt->address_strings[RPC_DISPLAY_NETID];
 		map->r_addr = rpc_sockaddr2uaddr(sap, GFP_ATOMIC);
+		if (!map->r_addr) {
+			status = -ENOMEM;
+			dprintk("RPC: %5u %s: no memory available\n",
+				task->tk_pid, __func__);
+			goto bailout_free_args;
+		}
 		map->r_owner = "";
 		break;
 	case RPCBVERS_2:
@@ -793,6 +799,8 @@ void rpcb_getport_async(struct rpc_task *task)
 	rpc_put_task(child);
 	return;
 
+bailout_free_args:
+	kfree(map);
 bailout_release_client:
 	rpc_release_client(rpcb_clnt);
 bailout_nofree:
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index f0b3700cec95..9cdbb6d6e7f5 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -48,6 +48,7 @@
 #include <net/udp.h>
 #include <net/tcp.h>
 #include <linux/bvec.h>
+#include <linux/highmem.h>
 #include <linux/uio.h>
 
 #include <trace/events/sunrpc.h>
@@ -380,6 +381,26 @@ xs_read_discard(struct socket *sock, struct msghdr *msg, int flags,
 	return sock_recvmsg(sock, msg, flags);
 }
 
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+static void
+xs_flush_bvec(const struct bio_vec *bvec, size_t count, size_t seek)
+{
+	struct bvec_iter bi = {
+		.bi_size = count,
+	};
+	struct bio_vec bv;
+
+	bvec_iter_advance(bvec, &bi, seek & PAGE_MASK);
+	for_each_bvec(bv, bvec, bi, bi)
+		flush_dcache_page(bv.bv_page);
+}
+#else
+static inline void
+xs_flush_bvec(const struct bio_vec *bvec, size_t count, size_t seek)
+{
+}
+#endif
+
 static ssize_t
 xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags,
 		struct xdr_buf *buf, size_t count, size_t seek, size_t *read)
@@ -413,6 +434,7 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags,
 				seek + buf->page_base);
 		if (ret <= 0)
 			goto sock_err;
+		xs_flush_bvec(buf->bvec, ret, seek + buf->page_base);
 		offset += ret - buf->page_base;
 		if (offset == count || msg->msg_flags & (MSG_EOR|MSG_TRUNC))
 			goto out;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 6376467e78f8..0b21187d74df 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -87,6 +87,11 @@ static int tipc_skb_tailroom(struct sk_buff *skb)
 	return limit;
 }
 
+static inline int TLV_GET_DATA_LEN(struct tlv_desc *tlv)
+{
+	return TLV_GET_LEN(tlv) - TLV_SPACE(0);
+}
+
 static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len)
 {
 	struct tlv_desc *tlv = (struct tlv_desc *)skb_tail_pointer(skb);
@@ -166,6 +171,11 @@ static struct sk_buff *tipc_get_err_tlv(char *str)
 	return buf;
 }
 
+static inline bool string_is_valid(char *s, int len)
+{
+	return memchr(s, '\0', len) ? true : false;
+}
+
 static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 				   struct tipc_nl_compat_msg *msg,
 				   struct sk_buff *arg)
@@ -379,6 +389,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd,
 	struct nlattr *prop;
 	struct nlattr *bearer;
 	struct tipc_bearer_config *b;
+	int len;
 
 	b = (struct tipc_bearer_config *)TLV_DATA(msg->req);
 
@@ -386,6 +397,10 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd,
 	if (!bearer)
 		return -EMSGSIZE;
 
+	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME);
+	if (!string_is_valid(b->name, len))
+		return -EINVAL;
+
 	if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, b->name))
 		return -EMSGSIZE;
 
@@ -411,6 +426,7 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd,
 {
 	char *name;
 	struct nlattr *bearer;
+	int len;
 
 	name = (char *)TLV_DATA(msg->req);
 
@@ -418,6 +434,10 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd,
 	if (!bearer)
 		return -EMSGSIZE;
 
+	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME);
+	if (!string_is_valid(name, len))
+		return -EINVAL;
+
 	if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, name))
 		return -EMSGSIZE;
 
@@ -478,6 +498,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 	struct nlattr *prop[TIPC_NLA_PROP_MAX + 1];
 	struct nlattr *stats[TIPC_NLA_STATS_MAX + 1];
 	int err;
+	int len;
 
 	if (!attrs[TIPC_NLA_LINK])
 		return -EINVAL;
@@ -504,6 +525,11 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 		return err;
 
 	name = (char *)TLV_DATA(msg->req);
+
+	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+	if (!string_is_valid(name, len))
+		return -EINVAL;
+
 	if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0)
 		return 0;
 
@@ -644,6 +670,7 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb,
 	struct nlattr *prop;
 	struct nlattr *media;
 	struct tipc_link_config *lc;
+	int len;
 
 	lc = (struct tipc_link_config *)TLV_DATA(msg->req);
 
@@ -651,6 +678,10 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb,
 	if (!media)
 		return -EMSGSIZE;
 
+	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME);
+	if (!string_is_valid(lc->name, len))
+		return -EINVAL;
+
 	if (nla_put_string(skb, TIPC_NLA_MEDIA_NAME, lc->name))
 		return -EMSGSIZE;
 
@@ -671,6 +702,7 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb,
 	struct nlattr *prop;
 	struct nlattr *bearer;
 	struct tipc_link_config *lc;
+	int len;
 
 	lc = (struct tipc_link_config *)TLV_DATA(msg->req);
 
@@ -678,6 +710,10 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb,
 	if (!bearer)
 		return -EMSGSIZE;
 
+	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME);
+	if (!string_is_valid(lc->name, len))
+		return -EINVAL;
+
 	if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, lc->name))
 		return -EMSGSIZE;
 
@@ -726,9 +762,14 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd,
 	struct tipc_link_config *lc;
 	struct tipc_bearer *bearer;
 	struct tipc_media *media;
+	int len;
 
 	lc = (struct tipc_link_config *)TLV_DATA(msg->req);
 
+	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+	if (!string_is_valid(lc->name, len))
+		return -EINVAL;
+
 	media = tipc_media_find(lc->name);
 	if (media) {
 		cmd->doit = &__tipc_nl_media_set;
@@ -750,6 +791,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd,
 {
 	char *name;
 	struct nlattr *link;
+	int len;
 
 	name = (char *)TLV_DATA(msg->req);
 
@@ -757,6 +799,10 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd,
 	if (!link)
 		return -EMSGSIZE;
 
+	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+	if (!string_is_valid(name, len))
+		return -EINVAL;
+
 	if (nla_put_string(skb, TIPC_NLA_LINK_NAME, name))
 		return -EMSGSIZE;
 
@@ -778,6 +824,8 @@ static int tipc_nl_compat_name_table_dump_header(struct tipc_nl_compat_msg *msg)
 	};
 
 	ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req);
+	if (TLV_GET_DATA_LEN(msg->req) < sizeof(struct tipc_name_table_query))
+		return -EINVAL;
 
 	depth = ntohl(ntq->depth);
 
@@ -1201,7 +1249,7 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
-	if (len && !TLV_OK(msg.req, len)) {
+	if (!len || !TLV_OK(msg.req, len)) {
 		msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
 		err = -EOPNOTSUPP;
 		goto send;
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index efb16f69bd2c..a457c0fbbef1 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -398,7 +398,7 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con)
 	ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT);
 	if (ret == -EWOULDBLOCK)
 		return -EWOULDBLOCK;
-	if (ret > 0) {
+	if (ret == sizeof(s)) {
 		read_lock_bh(&sk->sk_callback_lock);
 		ret = tipc_conn_rcv_sub(srv, con, &s);
 		read_unlock_bh(&sk->sk_callback_lock);
diff --git a/security/security.c b/security/security.c
index 04d173eb93f6..414a45d70c7b 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1014,6 +1014,13 @@ int security_cred_alloc_blank(struct cred *cred, gfp_t gfp)
 
 void security_cred_free(struct cred *cred)
 {
+	/*
+	 * There is a failure case in prepare_creds() that
+	 * may result in a call here with ->security being NULL.
+	 */
+	if (unlikely(cred->security == NULL))
+		return;
+
 	call_void_hook(cred_free, cred);
 }
 
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index b63ef865ce1e..d31a52e56b9e 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -732,7 +732,8 @@ static int sens_destroy(void *key, void *datum, void *p)
 	kfree(key);
 	if (datum) {
 		levdatum = datum;
-		ebitmap_destroy(&levdatum->level->cat);
+		if (levdatum->level)
+			ebitmap_destroy(&levdatum->level->cat);
 		kfree(levdatum->level);
 	}
 	kfree(datum);
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index ffda91a4a1aa..02514fe558b4 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -368,7 +368,9 @@ static int yama_ptrace_access_check(struct task_struct *child,
 			break;
 		case YAMA_SCOPE_RELATIONAL:
 			rcu_read_lock();
-			if (!task_is_descendant(current, child) &&
+			if (!pid_alive(child))
+				rc = -EPERM;
+			if (!rc && !task_is_descendant(current, child) &&
 			    !ptracer_exception_found(current, child) &&
 			    !ns_capable(__task_cred(child)->user_ns, CAP_SYS_PTRACE))
 				rc = -EPERM;